Hugging Face's logo

salym
/
rl_course_vizdoom_health_gathering_supreme

Reinforcement Learning
sample-factory
TensorBoard
deep-reinforcement-learning
Eval Results
Model card Files Metrics Community
salym commited on
Commit
8776c2a
·
verified ·
1 Parent(s): 757404b

Upload folder using huggingface_hub

Browse files
Files changed (9) hide show
  1. .gitattributes +1 -0
  2. .summary/0/events.out.tfevents.1742512771.60fe6b241b39 +3 -0
  3. README.md +56 -0
  4. checkpoint_p0/best_000000922_3776512_reward_25.425.pth +3 -0
  5. checkpoint_p0/checkpoint_000000912_3735552.pth +3 -0
  6. checkpoint_p0/checkpoint_000000978_4005888.pth +3 -0
  7. config.json +142 -0
  8. replay.mp4 +3 -0
  9. sf_log.txt +838 -0
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ replay.mp4 filter=lfs diff=lfs merge=lfs -text
.summary/0/events.out.tfevents.1742512771.60fe6b241b39 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:56c98b74810c5691d03b967fe9ae313811b683c68f081b0a1a8356afb36752c0
3
+ size 459790
README.md ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: sample-factory
3
+ tags:
4
+ - deep-reinforcement-learning
5
+ - reinforcement-learning
6
+ - sample-factory
7
+ model-index:
8
+ - name: APPO
9
+ results:
10
+ - task:
11
+ type: reinforcement-learning
12
+ name: reinforcement-learning
13
+ dataset:
14
+ name: doom_health_gathering_supreme
15
+ type: doom_health_gathering_supreme
16
+ metrics:
17
+ - type: mean_reward
18
+ value: 8.29 +/- 3.75
19
+ name: mean_reward
20
+ verified: false
21
+ ---
22
+
23
+ A(n) **APPO** model trained on the **doom_health_gathering_supreme** environment.
24
+
25
+ This model was trained using Sample-Factory 2.0: https://github.com/alex-petrenko/sample-factory.
26
+ Documentation for how to use Sample-Factory can be found at https://www.samplefactory.dev/
27
+
28
+
29
+ ## Downloading the model
30
+
31
+ After installing Sample-Factory, download the model with:
32
+ ```
33
+ python -m sample_factory.huggingface.load_from_hub -r salym/rl_course_vizdoom_health_gathering_supreme
34
+ ```
35
+
36
+
37
+ ## Using the model
38
+
39
+ To run the model after download, use the `enjoy` script corresponding to this environment:
40
+ ```
41
+ python -m <path.to.enjoy.module> --algo=APPO --env=doom_health_gathering_supreme --train_dir=./train_dir --experiment=rl_course_vizdoom_health_gathering_supreme
42
+ ```
43
+
44
+
45
+ You can also upload models to the Hugging Face Hub using the same script with the `--push_to_hub` flag.
46
+ See https://www.samplefactory.dev/10-huggingface/huggingface/ for more details
47
+
48
+ ## Training with this model
49
+
50
+ To continue training with this model, use the `train` script corresponding to this environment:
51
+ ```
52
+ python -m <path.to.train.module> --algo=APPO --env=doom_health_gathering_supreme --train_dir=./train_dir --experiment=rl_course_vizdoom_health_gathering_supreme --restart_behavior=resume --train_for_env_steps=10000000000
53
+ ```
54
+
55
+ Note, you may have to adjust `--train_for_env_steps` to a suitably high number as the experiment will resume at the number of steps it concluded at.
56
+
checkpoint_p0/best_000000922_3776512_reward_25.425.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2d8323a6c1a0310c01efd0811c4a28209e105d4b6324dc2323a938dc740696fd
3
+ size 34929051
checkpoint_p0/checkpoint_000000912_3735552.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4f4c80de1244d6586e2c7cf67dede3f95d33ceee4f453d51fbdd4d580f316278
3
+ size 34929541
checkpoint_p0/checkpoint_000000978_4005888.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:23f837bd8f26f89170eb57ebca93c8265d2ef5d633fdbb0e702809871078c561
3
+ size 34929541
config.json ADDED
@@ -0,0 +1,142 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "help": false,
3
+ "algo": "APPO",
4
+ "env": "doom_health_gathering_supreme",
5
+ "experiment": "default_experiment",
6
+ "train_dir": "/kaggle/working/train_dir",
7
+ "restart_behavior": "resume",
8
+ "device": "gpu",
9
+ "seed": null,
10
+ "num_policies": 1,
11
+ "async_rl": true,
12
+ "serial_mode": false,
13
+ "batched_sampling": false,
14
+ "num_batches_to_accumulate": 2,
15
+ "worker_num_splits": 2,
16
+ "policy_workers_per_policy": 1,
17
+ "max_policy_lag": 1000,
18
+ "num_workers": 8,
19
+ "num_envs_per_worker": 4,
20
+ "batch_size": 1024,
21
+ "num_batches_per_epoch": 1,
22
+ "num_epochs": 1,
23
+ "rollout": 32,
24
+ "recurrence": 32,
25
+ "shuffle_minibatches": false,
26
+ "gamma": 0.99,
27
+ "reward_scale": 1.0,
28
+ "reward_clip": 1000.0,
29
+ "value_bootstrap": false,
30
+ "normalize_returns": true,
31
+ "exploration_loss_coeff": 0.001,
32
+ "value_loss_coeff": 0.5,
33
+ "kl_loss_coeff": 0.0,
34
+ "exploration_loss": "symmetric_kl",
35
+ "gae_lambda": 0.95,
36
+ "ppo_clip_ratio": 0.1,
37
+ "ppo_clip_value": 0.2,
38
+ "with_vtrace": false,
39
+ "vtrace_rho": 1.0,
40
+ "vtrace_c": 1.0,
41
+ "optimizer": "adam",
42
+ "adam_eps": 1e-06,
43
+ "adam_beta1": 0.9,
44
+ "adam_beta2": 0.999,
45
+ "max_grad_norm": 4.0,
46
+ "learning_rate": 0.0001,
47
+ "lr_schedule": "constant",
48
+ "lr_schedule_kl_threshold": 0.008,
49
+ "lr_adaptive_min": 1e-06,
50
+ "lr_adaptive_max": 0.01,
51
+ "obs_subtract_mean": 0.0,
52
+ "obs_scale": 255.0,
53
+ "normalize_input": true,
54
+ "normalize_input_keys": null,
55
+ "decorrelate_experience_max_seconds": 0,
56
+ "decorrelate_envs_on_one_worker": true,
57
+ "actor_worker_gpus": [],
58
+ "set_workers_cpu_affinity": true,
59
+ "force_envs_single_thread": false,
60
+ "default_niceness": 0,
61
+ "log_to_file": true,
62
+ "experiment_summaries_interval": 10,
63
+ "flush_summaries_interval": 30,
64
+ "stats_avg": 100,
65
+ "summaries_use_frameskip": true,
66
+ "heartbeat_interval": 20,
67
+ "heartbeat_reporting_interval": 600,
68
+ "train_for_env_steps": 4000000,
69
+ "train_for_seconds": 10000000000,
70
+ "save_every_sec": 120,
71
+ "keep_checkpoints": 2,
72
+ "load_checkpoint_kind": "latest",
73
+ "save_milestones_sec": -1,
74
+ "save_best_every_sec": 5,
75
+ "save_best_metric": "reward",
76
+ "save_best_after": 100000,
77
+ "benchmark": false,
78
+ "encoder_mlp_layers": [
79
+ 512,
80
+ 512
81
+ ],
82
+ "encoder_conv_architecture": "convnet_simple",
83
+ "encoder_conv_mlp_layers": [
84
+ 512
85
+ ],
86
+ "use_rnn": true,
87
+ "rnn_size": 512,
88
+ "rnn_type": "gru",
89
+ "rnn_num_layers": 1,
90
+ "decoder_mlp_layers": [],
91
+ "nonlinearity": "elu",
92
+ "policy_initialization": "orthogonal",
93
+ "policy_init_gain": 1.0,
94
+ "actor_critic_share_weights": true,
95
+ "adaptive_stddev": true,
96
+ "continuous_tanh_scale": 0.0,
97
+ "initial_stddev": 1.0,
98
+ "use_env_info_cache": false,
99
+ "env_gpu_actions": false,
100
+ "env_gpu_observations": true,
101
+ "env_frameskip": 4,
102
+ "env_framestack": 1,
103
+ "pixel_format": "CHW",
104
+ "use_record_episode_statistics": false,
105
+ "with_wandb": false,
106
+ "wandb_user": null,
107
+ "wandb_project": "sample_factory",
108
+ "wandb_group": null,
109
+ "wandb_job_type": "SF",
110
+ "wandb_tags": [],
111
+ "with_pbt": false,
112
+ "pbt_mix_policies_in_one_env": true,
113
+ "pbt_period_env_steps": 5000000,
114
+ "pbt_start_mutation": 20000000,
115
+ "pbt_replace_fraction": 0.3,
116
+ "pbt_mutation_rate": 0.15,
117
+ "pbt_replace_reward_gap": 0.1,
118
+ "pbt_replace_reward_gap_absolute": 1e-06,
119
+ "pbt_optimize_gamma": false,
120
+ "pbt_target_objective": "true_objective",
121
+ "pbt_perturb_min": 1.1,
122
+ "pbt_perturb_max": 1.5,
123
+ "num_agents": -1,
124
+ "num_humans": 0,
125
+ "num_bots": -1,
126
+ "start_bot_difficulty": null,
127
+ "timelimit": null,
128
+ "res_w": 128,
129
+ "res_h": 72,
130
+ "wide_aspect_ratio": false,
131
+ "eval_env_frameskip": 1,
132
+ "fps": 35,
133
+ "command_line": "--env=doom_health_gathering_supreme --num_workers=8 --num_envs_per_worker=4 --train_for_env_steps=4000000",
134
+ "cli_args": {
135
+ "env": "doom_health_gathering_supreme",
136
+ "num_workers": 8,
137
+ "num_envs_per_worker": 4,
138
+ "train_for_env_steps": 4000000
139
+ },
140
+ "git_hash": "unknown",
141
+ "git_repo_name": "not a git repository"
142
+ }
replay.mp4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bb28de00566213c056958b6c7104fca92ef66097f062d041e19fd3d9a04a51df
3
+ size 15749053
sf_log.txt ADDED
@@ -0,0 +1,838 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [2025-03-20 23:19:36,745][00031] Saving configuration to /kaggle/working/train_dir/default_experiment/config.json...
2
+ [2025-03-20 23:19:36,747][00031] Rollout worker 0 uses device cpu
3
+ [2025-03-20 23:19:36,748][00031] Rollout worker 1 uses device cpu
4
+ [2025-03-20 23:19:36,749][00031] Rollout worker 2 uses device cpu
5
+ [2025-03-20 23:19:36,751][00031] Rollout worker 3 uses device cpu
6
+ [2025-03-20 23:19:36,752][00031] Rollout worker 4 uses device cpu
7
+ [2025-03-20 23:19:36,753][00031] Rollout worker 5 uses device cpu
8
+ [2025-03-20 23:19:36,753][00031] Rollout worker 6 uses device cpu
9
+ [2025-03-20 23:19:36,754][00031] Rollout worker 7 uses device cpu
10
+ [2025-03-20 23:19:36,931][00031] Using GPUs [0] for process 0 (actually maps to GPUs [0])
11
+ [2025-03-20 23:19:36,932][00031] InferenceWorker_p0-w0: min num requests: 2
12
+ [2025-03-20 23:19:36,981][00031] Starting all processes...
13
+ [2025-03-20 23:19:36,982][00031] Starting process learner_proc0
14
+ [2025-03-20 23:19:37,079][00031] Starting all processes...
15
+ [2025-03-20 23:19:37,090][00031] Starting process inference_proc0-0
16
+ [2025-03-20 23:19:37,092][00031] Starting process rollout_proc0
17
+ [2025-03-20 23:19:37,092][00031] Starting process rollout_proc1
18
+ [2025-03-20 23:19:37,093][00031] Starting process rollout_proc2
19
+ [2025-03-20 23:19:37,093][00031] Starting process rollout_proc3
20
+ [2025-03-20 23:19:37,093][00031] Starting process rollout_proc4
21
+ [2025-03-20 23:19:37,094][00031] Starting process rollout_proc5
22
+ [2025-03-20 23:19:37,094][00031] Starting process rollout_proc6
23
+ [2025-03-20 23:19:37,095][00031] Starting process rollout_proc7
24
+ [2025-03-20 23:19:45,156][00209] Using GPUs [0] for process 0 (actually maps to GPUs [0])
25
+ [2025-03-20 23:19:45,156][00209] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for inference process 0
26
+ [2025-03-20 23:19:45,246][00209] Num visible devices: 1
27
+ [2025-03-20 23:19:45,781][00214] Worker 4 uses CPU cores [0]
28
+ [2025-03-20 23:19:45,859][00211] Worker 1 uses CPU cores [1]
29
+ [2025-03-20 23:19:46,024][00196] Using GPUs [0] for process 0 (actually maps to GPUs [0])
30
+ [2025-03-20 23:19:46,024][00196] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for learning process 0
31
+ [2025-03-20 23:19:46,055][00196] Num visible devices: 1
32
+ [2025-03-20 23:19:46,063][00196] Starting seed is not provided
33
+ [2025-03-20 23:19:46,063][00196] Using GPUs [0] for process 0 (actually maps to GPUs [0])
34
+ [2025-03-20 23:19:46,064][00196] Initializing actor-critic model on device cuda:0
35
+ [2025-03-20 23:19:46,063][00210] Worker 0 uses CPU cores [0]
36
+ [2025-03-20 23:19:46,064][00196] RunningMeanStd input shape: (3, 72, 128)
37
+ [2025-03-20 23:19:46,069][00212] Worker 3 uses CPU cores [3]
38
+ [2025-03-20 23:19:46,070][00216] Worker 5 uses CPU cores [1]
39
+ [2025-03-20 23:19:46,074][00196] RunningMeanStd input shape: (1,)
40
+ [2025-03-20 23:19:46,095][00196] ConvEncoder: input_channels=3
41
+ [2025-03-20 23:19:46,188][00215] Worker 7 uses CPU cores [3]
42
+ [2025-03-20 23:19:46,230][00213] Worker 2 uses CPU cores [2]
43
+ [2025-03-20 23:19:46,266][00217] Worker 6 uses CPU cores [2]
44
+ [2025-03-20 23:19:46,481][00196] Conv encoder output size: 512
45
+ [2025-03-20 23:19:46,481][00196] Policy head output size: 512
46
+ [2025-03-20 23:19:46,563][00196] Created Actor Critic model with architecture:
47
+ [2025-03-20 23:19:46,563][00196] ActorCriticSharedWeights(
48
+ (obs_normalizer): ObservationNormalizer(
49
+ (running_mean_std): RunningMeanStdDictInPlace(
50
+ (running_mean_std): ModuleDict(
51
+ (obs): RunningMeanStdInPlace()
52
+ )
53
+ )
54
+ )
55
+ (returns_normalizer): RecursiveScriptModule(original_name=RunningMeanStdInPlace)
56
+ (encoder): VizdoomEncoder(
57
+ (basic_encoder): ConvEncoder(
58
+ (enc): RecursiveScriptModule(
59
+ original_name=ConvEncoderImpl
60
+ (conv_head): RecursiveScriptModule(
61
+ original_name=Sequential
62
+ (0): RecursiveScriptModule(original_name=Conv2d)
63
+ (1): RecursiveScriptModule(original_name=ELU)
64
+ (2): RecursiveScriptModule(original_name=Conv2d)
65
+ (3): RecursiveScriptModule(original_name=ELU)
66
+ (4): RecursiveScriptModule(original_name=Conv2d)
67
+ (5): RecursiveScriptModule(original_name=ELU)
68
+ )
69
+ (mlp_layers): RecursiveScriptModule(
70
+ original_name=Sequential
71
+ (0): RecursiveScriptModule(original_name=Linear)
72
+ (1): RecursiveScriptModule(original_name=ELU)
73
+ )
74
+ )
75
+ )
76
+ )
77
+ (core): ModelCoreRNN(
78
+ (core): GRU(512, 512)
79
+ )
80
+ (decoder): MlpDecoder(
81
+ (mlp): Identity()
82
+ )
83
+ (critic_linear): Linear(in_features=512, out_features=1, bias=True)
84
+ (action_parameterization): ActionParameterizationDefault(
85
+ (distribution_linear): Linear(in_features=512, out_features=5, bias=True)
86
+ )
87
+ )
88
+ [2025-03-20 23:19:47,019][00196] Using optimizer <class 'torch.optim.adam.Adam'>
89
+ [2025-03-20 23:19:49,228][00196] No checkpoints found
90
+ [2025-03-20 23:19:49,228][00196] Did not load from checkpoint, starting from scratch!
91
+ [2025-03-20 23:19:49,228][00196] Initialized policy 0 weights for model version 0
92
+ [2025-03-20 23:19:49,234][00196] LearnerWorker_p0 finished initialization!
93
+ [2025-03-20 23:19:49,235][00196] Using GPUs [0] for process 0 (actually maps to GPUs [0])
94
+ [2025-03-20 23:19:49,332][00209] RunningMeanStd input shape: (3, 72, 128)
95
+ [2025-03-20 23:19:49,333][00209] RunningMeanStd input shape: (1,)
96
+ [2025-03-20 23:19:49,345][00209] ConvEncoder: input_channels=3
97
+ [2025-03-20 23:19:49,492][00209] Conv encoder output size: 512
98
+ [2025-03-20 23:19:49,492][00209] Policy head output size: 512
99
+ [2025-03-20 23:19:49,592][00031] Inference worker 0-0 is ready!
100
+ [2025-03-20 23:19:49,593][00031] All inference workers are ready! Signal rollout workers to start!
101
+ [2025-03-20 23:19:49,722][00210] Doom resolution: 160x120, resize resolution: (128, 72)
102
+ [2025-03-20 23:19:49,724][00213] Doom resolution: 160x120, resize resolution: (128, 72)
103
+ [2025-03-20 23:19:49,722][00217] Doom resolution: 160x120, resize resolution: (128, 72)
104
+ [2025-03-20 23:19:49,725][00212] Doom resolution: 160x120, resize resolution: (128, 72)
105
+ [2025-03-20 23:19:49,726][00216] Doom resolution: 160x120, resize resolution: (128, 72)
106
+ [2025-03-20 23:19:49,724][00215] Doom resolution: 160x120, resize resolution: (128, 72)
107
+ [2025-03-20 23:19:49,728][00211] Doom resolution: 160x120, resize resolution: (128, 72)
108
+ [2025-03-20 23:19:49,725][00214] Doom resolution: 160x120, resize resolution: (128, 72)
109
+ [2025-03-20 23:19:50,513][00210] Decorrelating experience for 0 frames...
110
+ [2025-03-20 23:19:50,515][00214] Decorrelating experience for 0 frames...
111
+ [2025-03-20 23:19:50,833][00216] Decorrelating experience for 0 frames...
112
+ [2025-03-20 23:19:50,835][00212] Decorrelating experience for 0 frames...
113
+ [2025-03-20 23:19:50,831][00215] Decorrelating experience for 0 frames...
114
+ [2025-03-20 23:19:50,838][00211] Decorrelating experience for 0 frames...
115
+ [2025-03-20 23:19:51,107][00213] Decorrelating experience for 0 frames...
116
+ [2025-03-20 23:19:51,192][00031] Fps is (10 sec: nan, 60 sec: nan, 300 sec: nan). Total num frames: 0. Throughput: 0: nan. Samples: 0. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0)
117
+ [2025-03-20 23:19:51,555][00213] Decorrelating experience for 32 frames...
118
+ [2025-03-20 23:19:51,582][00214] Decorrelating experience for 32 frames...
119
+ [2025-03-20 23:19:51,695][00211] Decorrelating experience for 32 frames...
120
+ [2025-03-20 23:19:51,736][00215] Decorrelating experience for 32 frames...
121
+ [2025-03-20 23:19:51,740][00212] Decorrelating experience for 32 frames...
122
+ [2025-03-20 23:19:51,777][00216] Decorrelating experience for 32 frames...
123
+ [2025-03-20 23:19:52,192][00217] Decorrelating experience for 0 frames...
124
+ [2025-03-20 23:19:52,479][00211] Decorrelating experience for 64 frames...
125
+ [2025-03-20 23:19:52,497][00210] Decorrelating experience for 32 frames...
126
+ [2025-03-20 23:19:52,499][00214] Decorrelating experience for 64 frames...
127
+ [2025-03-20 23:19:52,797][00212] Decorrelating experience for 64 frames...
128
+ [2025-03-20 23:19:53,093][00215] Decorrelating experience for 64 frames...
129
+ [2025-03-20 23:19:53,155][00214] Decorrelating experience for 96 frames...
130
+ [2025-03-20 23:19:53,177][00213] Decorrelating experience for 64 frames...
131
+ [2025-03-20 23:19:53,437][00216] Decorrelating experience for 64 frames...
132
+ [2025-03-20 23:19:53,444][00211] Decorrelating experience for 96 frames...
133
+ [2025-03-20 23:19:53,506][00217] Decorrelating experience for 32 frames...
134
+ [2025-03-20 23:19:53,725][00210] Decorrelating experience for 64 frames...
135
+ [2025-03-20 23:19:53,847][00212] Decorrelating experience for 96 frames...
136
+ [2025-03-20 23:19:54,128][00216] Decorrelating experience for 96 frames...
137
+ [2025-03-20 23:19:54,191][00217] Decorrelating experience for 64 frames...
138
+ [2025-03-20 23:19:54,312][00215] Decorrelating experience for 96 frames...
139
+ [2025-03-20 23:19:54,337][00210] Decorrelating experience for 96 frames...
140
+ [2025-03-20 23:19:54,853][00217] Decorrelating experience for 96 frames...
141
+ [2025-03-20 23:19:54,946][00213] Decorrelating experience for 96 frames...
142
+ [2025-03-20 23:19:56,191][00031] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 0. Throughput: 0: 7.2. Samples: 36. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0)
143
+ [2025-03-20 23:19:56,193][00031] Avg episode reward: [(0, '0.480')]
144
+ [2025-03-20 23:19:56,919][00031] Heartbeat connected on Batcher_0
145
+ [2025-03-20 23:19:56,938][00031] Heartbeat connected on InferenceWorker_p0-w0
146
+ [2025-03-20 23:19:56,952][00031] Heartbeat connected on RolloutWorker_w0
147
+ [2025-03-20 23:19:56,966][00031] Heartbeat connected on RolloutWorker_w3
148
+ [2025-03-20 23:19:56,975][00031] Heartbeat connected on RolloutWorker_w4
149
+ [2025-03-20 23:19:56,977][00031] Heartbeat connected on RolloutWorker_w1
150
+ [2025-03-20 23:19:56,985][00031] Heartbeat connected on RolloutWorker_w5
151
+ [2025-03-20 23:19:56,993][00031] Heartbeat connected on RolloutWorker_w2
152
+ [2025-03-20 23:19:57,009][00031] Heartbeat connected on RolloutWorker_w6
153
+ [2025-03-20 23:19:57,036][00031] Heartbeat connected on RolloutWorker_w7
154
+ [2025-03-20 23:19:57,477][00196] Signal inference workers to stop experience collection...
155
+ [2025-03-20 23:19:57,483][00209] InferenceWorker_p0-w0: stopping experience collection
156
+ [2025-03-20 23:20:01,021][00196] Signal inference workers to resume experience collection...
157
+ [2025-03-20 23:20:01,022][00209] InferenceWorker_p0-w0: resuming experience collection
158
+ [2025-03-20 23:20:01,192][00031] Fps is (10 sec: 409.6, 60 sec: 409.6, 300 sec: 409.6). Total num frames: 4096. Throughput: 0: 252.4. Samples: 2524. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0)
159
+ [2025-03-20 23:20:01,194][00031] Avg episode reward: [(0, '1.960')]
160
+ [2025-03-20 23:20:01,673][00031] Heartbeat connected on LearnerWorker_p0
161
+ [2025-03-20 23:20:05,395][00209] Updated weights for policy 0, policy_version 10 (0.0178)
162
+ [2025-03-20 23:20:06,191][00031] Fps is (10 sec: 4505.6, 60 sec: 3003.7, 300 sec: 3003.7). Total num frames: 45056. Throughput: 0: 608.5. Samples: 9128. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
163
+ [2025-03-20 23:20:06,194][00031] Avg episode reward: [(0, '4.420')]
164
+ [2025-03-20 23:20:10,073][00209] Updated weights for policy 0, policy_version 20 (0.0015)
165
+ [2025-03-20 23:20:11,191][00031] Fps is (10 sec: 8601.7, 60 sec: 4505.6, 300 sec: 4505.6). Total num frames: 90112. Throughput: 0: 1101.5. Samples: 22030. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
166
+ [2025-03-20 23:20:11,194][00031] Avg episode reward: [(0, '4.262')]
167
+ [2025-03-20 23:20:15,010][00209] Updated weights for policy 0, policy_version 30 (0.0022)
168
+ [2025-03-20 23:20:16,191][00031] Fps is (10 sec: 8601.6, 60 sec: 5242.9, 300 sec: 5242.9). Total num frames: 131072. Throughput: 0: 1136.3. Samples: 28408. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
169
+ [2025-03-20 23:20:16,193][00031] Avg episode reward: [(0, '4.573')]
170
+ [2025-03-20 23:20:16,195][00196] Saving new best policy, reward=4.573!
171
+ [2025-03-20 23:20:20,235][00209] Updated weights for policy 0, policy_version 40 (0.0024)
172
+ [2025-03-20 23:20:21,193][00031] Fps is (10 sec: 7780.9, 60 sec: 5597.5, 300 sec: 5597.5). Total num frames: 167936. Throughput: 0: 1347.8. Samples: 40438. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
173
+ [2025-03-20 23:20:21,195][00031] Avg episode reward: [(0, '4.501')]
174
+ [2025-03-20 23:20:25,269][00209] Updated weights for policy 0, policy_version 50 (0.0017)
175
+ [2025-03-20 23:20:26,191][00031] Fps is (10 sec: 7782.4, 60 sec: 5968.5, 300 sec: 5968.5). Total num frames: 208896. Throughput: 0: 1498.4. Samples: 52444. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
176
+ [2025-03-20 23:20:26,194][00031] Avg episode reward: [(0, '4.422')]
177
+ [2025-03-20 23:20:30,023][00209] Updated weights for policy 0, policy_version 60 (0.0017)
178
+ [2025-03-20 23:20:31,192][00031] Fps is (10 sec: 8603.2, 60 sec: 6348.8, 300 sec: 6348.8). Total num frames: 253952. Throughput: 0: 1472.4. Samples: 58898. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
179
+ [2025-03-20 23:20:31,193][00031] Avg episode reward: [(0, '4.313')]
180
+ [2025-03-20 23:20:34,861][00209] Updated weights for policy 0, policy_version 70 (0.0019)
181
+ [2025-03-20 23:20:36,192][00031] Fps is (10 sec: 8601.2, 60 sec: 6553.5, 300 sec: 6553.5). Total num frames: 294912. Throughput: 0: 1593.1. Samples: 71690. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
182
+ [2025-03-20 23:20:36,196][00031] Avg episode reward: [(0, '4.593')]
183
+ [2025-03-20 23:20:36,197][00196] Saving new best policy, reward=4.593!
184
+ [2025-03-20 23:20:39,629][00209] Updated weights for policy 0, policy_version 80 (0.0016)
185
+ [2025-03-20 23:20:41,191][00031] Fps is (10 sec: 8601.7, 60 sec: 6799.4, 300 sec: 6799.4). Total num frames: 339968. Throughput: 0: 1879.0. Samples: 84592. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
186
+ [2025-03-20 23:20:41,197][00031] Avg episode reward: [(0, '4.300')]
187
+ [2025-03-20 23:20:44,362][00209] Updated weights for policy 0, policy_version 90 (0.0017)
188
+ [2025-03-20 23:20:46,192][00031] Fps is (10 sec: 8601.9, 60 sec: 6926.0, 300 sec: 6926.0). Total num frames: 380928. Throughput: 0: 1970.7. Samples: 91206. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
189
+ [2025-03-20 23:20:46,193][00031] Avg episode reward: [(0, '4.551')]
190
+ [2025-03-20 23:20:49,156][00209] Updated weights for policy 0, policy_version 100 (0.0020)
191
+ [2025-03-20 23:20:51,192][00031] Fps is (10 sec: 8601.6, 60 sec: 7099.7, 300 sec: 7099.7). Total num frames: 425984. Throughput: 0: 2106.4. Samples: 103916. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
192
+ [2025-03-20 23:20:51,193][00031] Avg episode reward: [(0, '4.711')]
193
+ [2025-03-20 23:20:51,202][00196] Saving new best policy, reward=4.711!
194
+ [2025-03-20 23:20:54,724][00209] Updated weights for policy 0, policy_version 110 (0.0021)
195
+ [2025-03-20 23:20:56,191][00031] Fps is (10 sec: 7782.4, 60 sec: 7645.9, 300 sec: 7057.7). Total num frames: 458752. Throughput: 0: 2068.6. Samples: 115116. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
196
+ [2025-03-20 23:20:56,196][00031] Avg episode reward: [(0, '4.548')]
197
+ [2025-03-20 23:20:59,603][00209] Updated weights for policy 0, policy_version 120 (0.0020)
198
+ [2025-03-20 23:21:01,191][00031] Fps is (10 sec: 7782.4, 60 sec: 8328.6, 300 sec: 7197.3). Total num frames: 503808. Throughput: 0: 2068.7. Samples: 121498. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0)
199
+ [2025-03-20 23:21:01,194][00031] Avg episode reward: [(0, '4.680')]
200
+ [2025-03-20 23:21:04,610][00209] Updated weights for policy 0, policy_version 130 (0.0022)
201
+ [2025-03-20 23:21:06,192][00031] Fps is (10 sec: 8601.6, 60 sec: 8328.5, 300 sec: 7263.6). Total num frames: 544768. Throughput: 0: 2076.4. Samples: 133872. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0)
202
+ [2025-03-20 23:21:06,193][00031] Avg episode reward: [(0, '4.874')]
203
+ [2025-03-20 23:21:06,196][00196] Saving new best policy, reward=4.874!
204
+ [2025-03-20 23:21:09,540][00209] Updated weights for policy 0, policy_version 140 (0.0022)
205
+ [2025-03-20 23:21:11,191][00031] Fps is (10 sec: 8192.0, 60 sec: 8260.3, 300 sec: 7321.6). Total num frames: 585728. Throughput: 0: 2086.2. Samples: 146324. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
206
+ [2025-03-20 23:21:11,193][00031] Avg episode reward: [(0, '4.931')]
207
+ [2025-03-20 23:21:11,200][00196] Saving new best policy, reward=4.931!
208
+ [2025-03-20 23:21:14,442][00209] Updated weights for policy 0, policy_version 150 (0.0017)
209
+ [2025-03-20 23:21:16,191][00031] Fps is (10 sec: 8192.0, 60 sec: 8260.3, 300 sec: 7372.8). Total num frames: 626688. Throughput: 0: 2082.4. Samples: 152606. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
210
+ [2025-03-20 23:21:16,193][00031] Avg episode reward: [(0, '4.952')]
211
+ [2025-03-20 23:21:16,196][00196] Saving new best policy, reward=4.952!
212
+ [2025-03-20 23:21:19,400][00209] Updated weights for policy 0, policy_version 160 (0.0018)
213
+ [2025-03-20 23:21:21,191][00031] Fps is (10 sec: 8192.0, 60 sec: 8328.8, 300 sec: 7418.3). Total num frames: 667648. Throughput: 0: 2073.3. Samples: 164986. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
214
+ [2025-03-20 23:21:21,193][00031] Avg episode reward: [(0, '5.211')]
215
+ [2025-03-20 23:21:21,200][00196] Saving new best policy, reward=5.211!
216
+ [2025-03-20 23:21:24,359][00209] Updated weights for policy 0, policy_version 170 (0.0021)
217
+ [2025-03-20 23:21:26,191][00031] Fps is (10 sec: 7782.4, 60 sec: 8260.3, 300 sec: 7415.9). Total num frames: 704512. Throughput: 0: 2044.7. Samples: 176604. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
218
+ [2025-03-20 23:21:26,193][00031] Avg episode reward: [(0, '5.174')]
219
+ [2025-03-20 23:21:29,762][00209] Updated weights for policy 0, policy_version 180 (0.0019)
220
+ [2025-03-20 23:21:31,192][00031] Fps is (10 sec: 8192.0, 60 sec: 8260.3, 300 sec: 7495.7). Total num frames: 749568. Throughput: 0: 2028.8. Samples: 182500. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
221
+ [2025-03-20 23:21:31,193][00031] Avg episode reward: [(0, '4.908')]
222
+ [2025-03-20 23:21:31,200][00196] Saving /kaggle/working/train_dir/default_experiment/checkpoint_p0/checkpoint_000000183_749568.pth...
223
+ [2025-03-20 23:21:34,601][00209] Updated weights for policy 0, policy_version 190 (0.0021)
224
+ [2025-03-20 23:21:36,191][00031] Fps is (10 sec: 8601.6, 60 sec: 8260.3, 300 sec: 7528.8). Total num frames: 790528. Throughput: 0: 2027.7. Samples: 195162. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
225
+ [2025-03-20 23:21:36,193][00031] Avg episode reward: [(0, '5.250')]
226
+ [2025-03-20 23:21:36,195][00196] Saving new best policy, reward=5.250!
227
+ [2025-03-20 23:21:39,684][00209] Updated weights for policy 0, policy_version 200 (0.0021)
228
+ [2025-03-20 23:21:41,192][00031] Fps is (10 sec: 8192.0, 60 sec: 8192.0, 300 sec: 7559.0). Total num frames: 831488. Throughput: 0: 2052.2. Samples: 207464. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
229
+ [2025-03-20 23:21:41,194][00031] Avg episode reward: [(0, '5.199')]
230
+ [2025-03-20 23:21:44,560][00209] Updated weights for policy 0, policy_version 210 (0.0019)
231
+ [2025-03-20 23:21:46,192][00031] Fps is (10 sec: 8192.0, 60 sec: 8192.0, 300 sec: 7586.5). Total num frames: 872448. Throughput: 0: 2048.8. Samples: 213694. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
232
+ [2025-03-20 23:21:46,193][00031] Avg episode reward: [(0, '5.217')]
233
+ [2025-03-20 23:21:49,484][00209] Updated weights for policy 0, policy_version 220 (0.0021)
234
+ [2025-03-20 23:21:51,192][00031] Fps is (10 sec: 8191.9, 60 sec: 8123.7, 300 sec: 7611.7). Total num frames: 913408. Throughput: 0: 2050.5. Samples: 226144. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
235
+ [2025-03-20 23:21:51,193][00031] Avg episode reward: [(0, '5.546')]
236
+ [2025-03-20 23:21:51,205][00196] Saving new best policy, reward=5.546!
237
+ [2025-03-20 23:21:54,594][00209] Updated weights for policy 0, policy_version 230 (0.0023)
238
+ [2025-03-20 23:21:56,191][00031] Fps is (10 sec: 8192.0, 60 sec: 8260.3, 300 sec: 7634.9). Total num frames: 954368. Throughput: 0: 2043.4. Samples: 238276. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
239
+ [2025-03-20 23:21:56,194][00031] Avg episode reward: [(0, '5.609')]
240
+ [2025-03-20 23:21:56,195][00196] Saving new best policy, reward=5.609!
241
+ [2025-03-20 23:22:00,200][00209] Updated weights for policy 0, policy_version 240 (0.0025)
242
+ [2025-03-20 23:22:01,192][00031] Fps is (10 sec: 7372.9, 60 sec: 8055.5, 300 sec: 7593.4). Total num frames: 987136. Throughput: 0: 2017.0. Samples: 243372. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
243
+ [2025-03-20 23:22:01,195][00031] Avg episode reward: [(0, '5.573')]
244
+ [2025-03-20 23:22:05,134][00209] Updated weights for policy 0, policy_version 250 (0.0019)
245
+ [2025-03-20 23:22:06,192][00031] Fps is (10 sec: 7782.3, 60 sec: 8123.7, 300 sec: 7645.9). Total num frames: 1032192. Throughput: 0: 2011.2. Samples: 255490. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
246
+ [2025-03-20 23:22:06,194][00031] Avg episode reward: [(0, '6.401')]
247
+ [2025-03-20 23:22:06,197][00196] Saving new best policy, reward=6.401!
248
+ [2025-03-20 23:22:09,983][00209] Updated weights for policy 0, policy_version 260 (0.0021)
249
+ [2025-03-20 23:22:11,192][00031] Fps is (10 sec: 8601.6, 60 sec: 8123.7, 300 sec: 7665.4). Total num frames: 1073152. Throughput: 0: 2037.2. Samples: 268280. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
250
+ [2025-03-20 23:22:11,194][00031] Avg episode reward: [(0, '7.509')]
251
+ [2025-03-20 23:22:11,203][00196] Saving new best policy, reward=7.509!
252
+ [2025-03-20 23:22:14,833][00209] Updated weights for policy 0, policy_version 270 (0.0017)
253
+ [2025-03-20 23:22:16,191][00031] Fps is (10 sec: 8192.1, 60 sec: 8123.7, 300 sec: 7683.5). Total num frames: 1114112. Throughput: 0: 2051.2. Samples: 274804. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
254
+ [2025-03-20 23:22:16,195][00031] Avg episode reward: [(0, '7.105')]
255
+ [2025-03-20 23:22:19,669][00209] Updated weights for policy 0, policy_version 280 (0.0017)
256
+ [2025-03-20 23:22:21,191][00031] Fps is (10 sec: 8601.6, 60 sec: 8192.0, 300 sec: 7727.8). Total num frames: 1159168. Throughput: 0: 2047.6. Samples: 287302. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
257
+ [2025-03-20 23:22:21,193][00031] Avg episode reward: [(0, '7.271')]
258
+ [2025-03-20 23:22:24,373][00209] Updated weights for policy 0, policy_version 290 (0.0022)
259
+ [2025-03-20 23:22:26,192][00031] Fps is (10 sec: 8601.6, 60 sec: 8260.3, 300 sec: 7742.8). Total num frames: 1200128. Throughput: 0: 2060.4. Samples: 300182. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
260
+ [2025-03-20 23:22:26,193][00031] Avg episode reward: [(0, '7.034')]
261
+ [2025-03-20 23:22:29,294][00209] Updated weights for policy 0, policy_version 300 (0.0019)
262
+ [2025-03-20 23:22:31,191][00031] Fps is (10 sec: 8192.0, 60 sec: 8192.0, 300 sec: 7756.8). Total num frames: 1241088. Throughput: 0: 2061.0. Samples: 306438. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
263
+ [2025-03-20 23:22:31,195][00031] Avg episode reward: [(0, '7.088')]
264
+ [2025-03-20 23:22:34,891][00209] Updated weights for policy 0, policy_version 310 (0.0023)
265
+ [2025-03-20 23:22:36,191][00031] Fps is (10 sec: 7782.4, 60 sec: 8123.7, 300 sec: 7745.2). Total num frames: 1277952. Throughput: 0: 2032.4. Samples: 317602. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
266
+ [2025-03-20 23:22:36,193][00031] Avg episode reward: [(0, '7.653')]
267
+ [2025-03-20 23:22:36,195][00196] Saving new best policy, reward=7.653!
268
+ [2025-03-20 23:22:39,651][00209] Updated weights for policy 0, policy_version 320 (0.0021)
269
+ [2025-03-20 23:22:41,192][00031] Fps is (10 sec: 8192.0, 60 sec: 8192.0, 300 sec: 7782.4). Total num frames: 1323008. Throughput: 0: 2046.8. Samples: 330384. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
270
+ [2025-03-20 23:22:41,193][00031] Avg episode reward: [(0, '8.664')]
271
+ [2025-03-20 23:22:41,202][00196] Saving new best policy, reward=8.664!
272
+ [2025-03-20 23:22:44,483][00209] Updated weights for policy 0, policy_version 330 (0.0015)
273
+ [2025-03-20 23:22:46,191][00031] Fps is (10 sec: 8601.6, 60 sec: 8192.0, 300 sec: 7794.1). Total num frames: 1363968. Throughput: 0: 2076.4. Samples: 336808. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
274
+ [2025-03-20 23:22:46,193][00031] Avg episode reward: [(0, '9.296')]
275
+ [2025-03-20 23:22:46,195][00196] Saving new best policy, reward=9.296!
276
+ [2025-03-20 23:22:49,110][00209] Updated weights for policy 0, policy_version 340 (0.0020)
277
+ [2025-03-20 23:22:51,192][00031] Fps is (10 sec: 8601.6, 60 sec: 8260.3, 300 sec: 7827.9). Total num frames: 1409024. Throughput: 0: 2094.7. Samples: 349752. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
278
+ [2025-03-20 23:22:51,193][00031] Avg episode reward: [(0, '10.283')]
279
+ [2025-03-20 23:22:51,200][00196] Saving new best policy, reward=10.283!
280
+ [2025-03-20 23:22:53,905][00209] Updated weights for policy 0, policy_version 350 (0.0019)
281
+ [2025-03-20 23:22:56,191][00031] Fps is (10 sec: 8601.6, 60 sec: 8260.3, 300 sec: 7837.8). Total num frames: 1449984. Throughput: 0: 2096.4. Samples: 362618. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
282
+ [2025-03-20 23:22:56,195][00031] Avg episode reward: [(0, '10.114')]
283
+ [2025-03-20 23:22:58,626][00209] Updated weights for policy 0, policy_version 360 (0.0017)
284
+ [2025-03-20 23:23:01,192][00031] Fps is (10 sec: 8601.6, 60 sec: 8465.1, 300 sec: 7868.6). Total num frames: 1495040. Throughput: 0: 2096.8. Samples: 369158. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
285
+ [2025-03-20 23:23:01,193][00031] Avg episode reward: [(0, '9.692')]
286
+ [2025-03-20 23:23:03,747][00209] Updated weights for policy 0, policy_version 370 (0.0019)
287
+ [2025-03-20 23:23:06,191][00031] Fps is (10 sec: 8192.0, 60 sec: 8328.5, 300 sec: 7855.9). Total num frames: 1531904. Throughput: 0: 2077.3. Samples: 380780. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
288
+ [2025-03-20 23:23:06,194][00031] Avg episode reward: [(0, '9.835')]
289
+ [2025-03-20 23:23:08,721][00209] Updated weights for policy 0, policy_version 380 (0.0017)
290
+ [2025-03-20 23:23:11,192][00031] Fps is (10 sec: 8192.0, 60 sec: 8396.8, 300 sec: 7884.8). Total num frames: 1576960. Throughput: 0: 2084.1. Samples: 393968. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
291
+ [2025-03-20 23:23:11,193][00031] Avg episode reward: [(0, '10.499')]
292
+ [2025-03-20 23:23:11,202][00196] Saving new best policy, reward=10.499!
293
+ [2025-03-20 23:23:13,304][00209] Updated weights for policy 0, policy_version 390 (0.0016)
294
+ [2025-03-20 23:23:16,192][00031] Fps is (10 sec: 8601.0, 60 sec: 8396.7, 300 sec: 7892.3). Total num frames: 1617920. Throughput: 0: 2092.0. Samples: 400578. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
295
+ [2025-03-20 23:23:16,194][00031] Avg episode reward: [(0, '11.811')]
296
+ [2025-03-20 23:23:16,239][00196] Saving new best policy, reward=11.811!
297
+ [2025-03-20 23:23:18,148][00209] Updated weights for policy 0, policy_version 400 (0.0019)
298
+ [2025-03-20 23:23:21,192][00031] Fps is (10 sec: 8601.5, 60 sec: 8396.8, 300 sec: 7918.9). Total num frames: 1662976. Throughput: 0: 2129.4. Samples: 413424. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
299
+ [2025-03-20 23:23:21,193][00031] Avg episode reward: [(0, '11.596')]
300
+ [2025-03-20 23:23:23,052][00209] Updated weights for policy 0, policy_version 410 (0.0022)
301
+ [2025-03-20 23:23:26,191][00031] Fps is (10 sec: 8602.3, 60 sec: 8396.8, 300 sec: 7925.3). Total num frames: 1703936. Throughput: 0: 2120.6. Samples: 425810. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
302
+ [2025-03-20 23:23:26,193][00031] Avg episode reward: [(0, '12.985')]
303
+ [2025-03-20 23:23:26,196][00196] Saving new best policy, reward=12.985!
304
+ [2025-03-20 23:23:27,912][00209] Updated weights for policy 0, policy_version 420 (0.0021)
305
+ [2025-03-20 23:23:31,192][00031] Fps is (10 sec: 8192.1, 60 sec: 8396.8, 300 sec: 7931.3). Total num frames: 1744896. Throughput: 0: 2118.7. Samples: 432148. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
306
+ [2025-03-20 23:23:31,193][00031] Avg episode reward: [(0, '13.206')]
307
+ [2025-03-20 23:23:31,232][00196] Saving /kaggle/working/train_dir/default_experiment/checkpoint_p0/checkpoint_000000427_1748992.pth...
308
+ [2025-03-20 23:23:31,322][00196] Saving new best policy, reward=13.206!
309
+ [2025-03-20 23:23:32,714][00209] Updated weights for policy 0, policy_version 430 (0.0016)
310
+ [2025-03-20 23:23:36,191][00031] Fps is (10 sec: 8191.9, 60 sec: 8465.1, 300 sec: 7937.1). Total num frames: 1785856. Throughput: 0: 2114.0. Samples: 444884. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
311
+ [2025-03-20 23:23:36,193][00031] Avg episode reward: [(0, '11.918')]
312
+ [2025-03-20 23:23:38,074][00209] Updated weights for policy 0, policy_version 440 (0.0018)
313
+ [2025-03-20 23:23:41,192][00031] Fps is (10 sec: 8192.0, 60 sec: 8396.8, 300 sec: 7942.7). Total num frames: 1826816. Throughput: 0: 2090.4. Samples: 456686. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
314
+ [2025-03-20 23:23:41,193][00031] Avg episode reward: [(0, '11.875')]
315
+ [2025-03-20 23:23:42,797][00209] Updated weights for policy 0, policy_version 450 (0.0020)
316
+ [2025-03-20 23:23:46,192][00031] Fps is (10 sec: 8601.6, 60 sec: 8465.1, 300 sec: 7965.4). Total num frames: 1871872. Throughput: 0: 2091.2. Samples: 463262. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
317
+ [2025-03-20 23:23:46,193][00031] Avg episode reward: [(0, '13.640')]
318
+ [2025-03-20 23:23:46,196][00196] Saving new best policy, reward=13.640!
319
+ [2025-03-20 23:23:47,534][00209] Updated weights for policy 0, policy_version 460 (0.0015)
320
+ [2025-03-20 23:23:51,192][00031] Fps is (10 sec: 9011.2, 60 sec: 8465.1, 300 sec: 7987.2). Total num frames: 1916928. Throughput: 0: 2123.5. Samples: 476336. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
321
+ [2025-03-20 23:23:51,194][00031] Avg episode reward: [(0, '14.054')]
322
+ [2025-03-20 23:23:51,204][00196] Saving new best policy, reward=14.054!
323
+ [2025-03-20 23:23:52,154][00209] Updated weights for policy 0, policy_version 470 (0.0016)
324
+ [2025-03-20 23:23:56,191][00031] Fps is (10 sec: 8601.7, 60 sec: 8465.1, 300 sec: 7991.4). Total num frames: 1957888. Throughput: 0: 2118.4. Samples: 489294. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
325
+ [2025-03-20 23:23:56,193][00031] Avg episode reward: [(0, '14.170')]
326
+ [2025-03-20 23:23:56,195][00196] Saving new best policy, reward=14.170!
327
+ [2025-03-20 23:23:56,937][00209] Updated weights for policy 0, policy_version 480 (0.0018)
328
+ [2025-03-20 23:24:01,192][00031] Fps is (10 sec: 8601.6, 60 sec: 8465.1, 300 sec: 8011.8). Total num frames: 2002944. Throughput: 0: 2119.2. Samples: 495942. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
329
+ [2025-03-20 23:24:01,193][00031] Avg episode reward: [(0, '13.687')]
330
+ [2025-03-20 23:24:01,625][00209] Updated weights for policy 0, policy_version 490 (0.0017)
331
+ [2025-03-20 23:24:06,192][00031] Fps is (10 sec: 8191.9, 60 sec: 8465.1, 300 sec: 7999.2). Total num frames: 2039808. Throughput: 0: 2105.7. Samples: 508180. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
332
+ [2025-03-20 23:24:06,194][00031] Avg episode reward: [(0, '14.986')]
333
+ [2025-03-20 23:24:06,196][00196] Saving new best policy, reward=14.986!
334
+ [2025-03-20 23:24:06,870][00209] Updated weights for policy 0, policy_version 500 (0.0021)
335
+ [2025-03-20 23:24:11,192][00031] Fps is (10 sec: 7372.8, 60 sec: 8328.5, 300 sec: 7987.2). Total num frames: 2076672. Throughput: 0: 2073.6. Samples: 519124. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
336
+ [2025-03-20 23:24:11,196][00031] Avg episode reward: [(0, '14.611')]
337
+ [2025-03-20 23:24:12,423][00209] Updated weights for policy 0, policy_version 510 (0.0018)
338
+ [2025-03-20 23:24:16,192][00031] Fps is (10 sec: 7782.4, 60 sec: 8328.6, 300 sec: 7991.1). Total num frames: 2117632. Throughput: 0: 2072.4. Samples: 525406. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
339
+ [2025-03-20 23:24:16,193][00031] Avg episode reward: [(0, '14.892')]
340
+ [2025-03-20 23:24:17,366][00209] Updated weights for policy 0, policy_version 520 (0.0018)
341
+ [2025-03-20 23:24:21,192][00031] Fps is (10 sec: 8192.0, 60 sec: 8260.3, 300 sec: 7994.8). Total num frames: 2158592. Throughput: 0: 2061.6. Samples: 537658. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
342
+ [2025-03-20 23:24:21,193][00031] Avg episode reward: [(0, '14.450')]
343
+ [2025-03-20 23:24:22,326][00209] Updated weights for policy 0, policy_version 530 (0.0020)
344
+ [2025-03-20 23:24:26,192][00031] Fps is (10 sec: 8192.0, 60 sec: 8260.2, 300 sec: 7998.4). Total num frames: 2199552. Throughput: 0: 2080.0. Samples: 550286. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
345
+ [2025-03-20 23:24:26,194][00031] Avg episode reward: [(0, '14.373')]
346
+ [2025-03-20 23:24:27,258][00209] Updated weights for policy 0, policy_version 540 (0.0023)
347
+ [2025-03-20 23:24:31,193][00031] Fps is (10 sec: 8600.2, 60 sec: 8328.3, 300 sec: 8016.4). Total num frames: 2244608. Throughput: 0: 2073.6. Samples: 556576. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
348
+ [2025-03-20 23:24:31,196][00031] Avg episode reward: [(0, '16.230')]
349
+ [2025-03-20 23:24:31,206][00196] Saving new best policy, reward=16.230!
350
+ [2025-03-20 23:24:32,038][00209] Updated weights for policy 0, policy_version 550 (0.0021)
351
+ [2025-03-20 23:24:36,192][00031] Fps is (10 sec: 8601.5, 60 sec: 8328.5, 300 sec: 8019.5). Total num frames: 2285568. Throughput: 0: 2057.7. Samples: 568932. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
352
+ [2025-03-20 23:24:36,194][00031] Avg episode reward: [(0, '16.307')]
353
+ [2025-03-20 23:24:36,196][00196] Saving new best policy, reward=16.307!
354
+ [2025-03-20 23:24:37,110][00209] Updated weights for policy 0, policy_version 560 (0.0021)
355
+ [2025-03-20 23:24:41,192][00031] Fps is (10 sec: 7783.6, 60 sec: 8260.3, 300 sec: 8008.4). Total num frames: 2322432. Throughput: 0: 2036.8. Samples: 580950. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
356
+ [2025-03-20 23:24:41,193][00031] Avg episode reward: [(0, '17.741')]
357
+ [2025-03-20 23:24:41,203][00196] Saving new best policy, reward=17.741!
358
+ [2025-03-20 23:24:42,849][00209] Updated weights for policy 0, policy_version 570 (0.0021)
359
+ [2025-03-20 23:24:46,192][00031] Fps is (10 sec: 7373.0, 60 sec: 8123.7, 300 sec: 7997.6). Total num frames: 2359296. Throughput: 0: 1999.6. Samples: 585922. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
360
+ [2025-03-20 23:24:46,193][00031] Avg episode reward: [(0, '19.315')]
361
+ [2025-03-20 23:24:46,245][00196] Saving new best policy, reward=19.315!
362
+ [2025-03-20 23:24:47,822][00209] Updated weights for policy 0, policy_version 580 (0.0019)
363
+ [2025-03-20 23:24:51,192][00031] Fps is (10 sec: 7782.4, 60 sec: 8055.5, 300 sec: 8136.5). Total num frames: 2400256. Throughput: 0: 2001.3. Samples: 598240. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
364
+ [2025-03-20 23:24:51,195][00031] Avg episode reward: [(0, '20.525')]
365
+ [2025-03-20 23:24:51,243][00196] Saving new best policy, reward=20.525!
366
+ [2025-03-20 23:24:52,760][00209] Updated weights for policy 0, policy_version 590 (0.0018)
367
+ [2025-03-20 23:24:56,194][00031] Fps is (10 sec: 8189.6, 60 sec: 8055.1, 300 sec: 8261.3). Total num frames: 2441216. Throughput: 0: 2037.2. Samples: 610804. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
368
+ [2025-03-20 23:24:56,196][00031] Avg episode reward: [(0, '17.832')]
369
+ [2025-03-20 23:24:57,605][00209] Updated weights for policy 0, policy_version 600 (0.0020)
370
+ [2025-03-20 23:25:01,192][00031] Fps is (10 sec: 8601.1, 60 sec: 8055.4, 300 sec: 8275.3). Total num frames: 2486272. Throughput: 0: 2039.4. Samples: 617180. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
371
+ [2025-03-20 23:25:01,195][00031] Avg episode reward: [(0, '18.298')]
372
+ [2025-03-20 23:25:02,588][00209] Updated weights for policy 0, policy_version 610 (0.0019)
373
+ [2025-03-20 23:25:06,192][00031] Fps is (10 sec: 8603.6, 60 sec: 8123.7, 300 sec: 8261.4). Total num frames: 2527232. Throughput: 0: 2036.2. Samples: 629288. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
374
+ [2025-03-20 23:25:06,194][00031] Avg episode reward: [(0, '19.394')]
375
+ [2025-03-20 23:25:07,753][00209] Updated weights for policy 0, policy_version 620 (0.0026)
376
+ [2025-03-20 23:25:11,191][00031] Fps is (10 sec: 7782.9, 60 sec: 8123.7, 300 sec: 8247.5). Total num frames: 2564096. Throughput: 0: 2023.9. Samples: 641360. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
377
+ [2025-03-20 23:25:11,195][00031] Avg episode reward: [(0, '19.009')]
378
+ [2025-03-20 23:25:12,806][00209] Updated weights for policy 0, policy_version 630 (0.0022)
379
+ [2025-03-20 23:25:16,192][00031] Fps is (10 sec: 7373.2, 60 sec: 8055.5, 300 sec: 8247.6). Total num frames: 2600960. Throughput: 0: 2011.8. Samples: 647102. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
380
+ [2025-03-20 23:25:16,193][00031] Avg episode reward: [(0, '19.067')]
381
+ [2025-03-20 23:25:18,485][00209] Updated weights for policy 0, policy_version 640 (0.0022)
382
+ [2025-03-20 23:25:21,192][00031] Fps is (10 sec: 7782.1, 60 sec: 8055.4, 300 sec: 8247.5). Total num frames: 2641920. Throughput: 0: 1987.6. Samples: 658372. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
383
+ [2025-03-20 23:25:21,194][00031] Avg episode reward: [(0, '20.089')]
384
+ [2025-03-20 23:25:23,346][00209] Updated weights for policy 0, policy_version 650 (0.0017)
385
+ [2025-03-20 23:25:26,192][00031] Fps is (10 sec: 8191.9, 60 sec: 8055.5, 300 sec: 8233.7). Total num frames: 2682880. Throughput: 0: 1996.8. Samples: 670804. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
386
+ [2025-03-20 23:25:26,194][00031] Avg episode reward: [(0, '19.902')]
387
+ [2025-03-20 23:25:28,330][00209] Updated weights for policy 0, policy_version 660 (0.0019)
388
+ [2025-03-20 23:25:31,192][00031] Fps is (10 sec: 8192.2, 60 sec: 7987.4, 300 sec: 8233.7). Total num frames: 2723840. Throughput: 0: 2023.1. Samples: 676962. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
389
+ [2025-03-20 23:25:31,193][00031] Avg episode reward: [(0, '17.639')]
390
+ [2025-03-20 23:25:31,206][00196] Saving /kaggle/working/train_dir/default_experiment/checkpoint_p0/checkpoint_000000665_2723840.pth...
391
+ [2025-03-20 23:25:31,307][00196] Removing /kaggle/working/train_dir/default_experiment/checkpoint_p0/checkpoint_000000183_749568.pth
392
+ [2025-03-20 23:25:33,342][00209] Updated weights for policy 0, policy_version 670 (0.0019)
393
+ [2025-03-20 23:25:36,192][00031] Fps is (10 sec: 8192.0, 60 sec: 7987.2, 300 sec: 8219.8). Total num frames: 2764800. Throughput: 0: 2022.0. Samples: 689230. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
394
+ [2025-03-20 23:25:36,194][00031] Avg episode reward: [(0, '18.091')]
395
+ [2025-03-20 23:25:38,362][00209] Updated weights for policy 0, policy_version 680 (0.0021)
396
+ [2025-03-20 23:25:41,192][00031] Fps is (10 sec: 8192.1, 60 sec: 8055.5, 300 sec: 8219.8). Total num frames: 2805760. Throughput: 0: 2018.4. Samples: 701628. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
397
+ [2025-03-20 23:25:41,193][00031] Avg episode reward: [(0, '18.440')]
398
+ [2025-03-20 23:25:43,264][00209] Updated weights for policy 0, policy_version 690 (0.0016)
399
+ [2025-03-20 23:25:46,192][00031] Fps is (10 sec: 8601.6, 60 sec: 8192.0, 300 sec: 8219.8). Total num frames: 2850816. Throughput: 0: 2018.3. Samples: 708000. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
400
+ [2025-03-20 23:25:46,193][00031] Avg episode reward: [(0, '20.095')]
401
+ [2025-03-20 23:25:48,113][00209] Updated weights for policy 0, policy_version 700 (0.0021)
402
+ [2025-03-20 23:25:51,191][00031] Fps is (10 sec: 8601.7, 60 sec: 8192.0, 300 sec: 8247.5). Total num frames: 2891776. Throughput: 0: 2026.8. Samples: 720494. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
403
+ [2025-03-20 23:25:51,193][00031] Avg episode reward: [(0, '21.955')]
404
+ [2025-03-20 23:25:51,203][00196] Saving new best policy, reward=21.955!
405
+ [2025-03-20 23:25:53,029][00209] Updated weights for policy 0, policy_version 710 (0.0020)
406
+ [2025-03-20 23:25:56,192][00031] Fps is (10 sec: 8191.8, 60 sec: 8192.4, 300 sec: 8233.6). Total num frames: 2932736. Throughput: 0: 2035.3. Samples: 732950. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
407
+ [2025-03-20 23:25:56,195][00031] Avg episode reward: [(0, '21.615')]
408
+ [2025-03-20 23:25:57,848][00209] Updated weights for policy 0, policy_version 720 (0.0018)
409
+ [2025-03-20 23:26:01,192][00031] Fps is (10 sec: 8192.0, 60 sec: 8123.8, 300 sec: 8233.7). Total num frames: 2973696. Throughput: 0: 2049.2. Samples: 739316. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
410
+ [2025-03-20 23:26:01,193][00031] Avg episode reward: [(0, '19.206')]
411
+ [2025-03-20 23:26:02,846][00209] Updated weights for policy 0, policy_version 730 (0.0021)
412
+ [2025-03-20 23:26:06,191][00031] Fps is (10 sec: 8192.2, 60 sec: 8123.8, 300 sec: 8233.7). Total num frames: 3014656. Throughput: 0: 2078.1. Samples: 751888. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
413
+ [2025-03-20 23:26:06,193][00031] Avg episode reward: [(0, '20.423')]
414
+ [2025-03-20 23:26:07,766][00209] Updated weights for policy 0, policy_version 740 (0.0018)
415
+ [2025-03-20 23:26:11,192][00031] Fps is (10 sec: 8192.0, 60 sec: 8192.0, 300 sec: 8233.7). Total num frames: 3055616. Throughput: 0: 2078.4. Samples: 764330. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
416
+ [2025-03-20 23:26:11,195][00031] Avg episode reward: [(0, '19.765')]
417
+ [2025-03-20 23:26:12,643][00209] Updated weights for policy 0, policy_version 750 (0.0019)
418
+ [2025-03-20 23:26:16,191][00031] Fps is (10 sec: 8601.6, 60 sec: 8328.5, 300 sec: 8247.5). Total num frames: 3100672. Throughput: 0: 2080.6. Samples: 770590. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
419
+ [2025-03-20 23:26:16,193][00031] Avg episode reward: [(0, '19.285')]
420
+ [2025-03-20 23:26:17,546][00209] Updated weights for policy 0, policy_version 760 (0.0017)
421
+ [2025-03-20 23:26:21,192][00031] Fps is (10 sec: 8601.6, 60 sec: 8328.6, 300 sec: 8261.4). Total num frames: 3141632. Throughput: 0: 2087.9. Samples: 783184. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
422
+ [2025-03-20 23:26:21,193][00031] Avg episode reward: [(0, '18.202')]
423
+ [2025-03-20 23:26:22,405][00209] Updated weights for policy 0, policy_version 770 (0.0023)
424
+ [2025-03-20 23:26:26,191][00031] Fps is (10 sec: 8192.0, 60 sec: 8328.5, 300 sec: 8247.5). Total num frames: 3182592. Throughput: 0: 2090.1. Samples: 795684. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
425
+ [2025-03-20 23:26:26,193][00031] Avg episode reward: [(0, '19.639')]
426
+ [2025-03-20 23:26:27,354][00209] Updated weights for policy 0, policy_version 780 (0.0019)
427
+ [2025-03-20 23:26:31,192][00031] Fps is (10 sec: 8601.5, 60 sec: 8396.8, 300 sec: 8261.4). Total num frames: 3227648. Throughput: 0: 2091.0. Samples: 802096. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
428
+ [2025-03-20 23:26:31,193][00031] Avg episode reward: [(0, '21.499')]
429
+ [2025-03-20 23:26:32,098][00209] Updated weights for policy 0, policy_version 790 (0.0019)
430
+ [2025-03-20 23:26:36,192][00031] Fps is (10 sec: 8601.6, 60 sec: 8396.8, 300 sec: 8261.4). Total num frames: 3268608. Throughput: 0: 2094.8. Samples: 814762. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
431
+ [2025-03-20 23:26:36,193][00031] Avg episode reward: [(0, '23.525')]
432
+ [2025-03-20 23:26:36,201][00196] Saving new best policy, reward=23.525!
433
+ [2025-03-20 23:26:37,049][00209] Updated weights for policy 0, policy_version 800 (0.0020)
434
+ [2025-03-20 23:26:41,192][00031] Fps is (10 sec: 8191.3, 60 sec: 8396.7, 300 sec: 8261.4). Total num frames: 3309568. Throughput: 0: 2091.1. Samples: 827050. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
435
+ [2025-03-20 23:26:41,194][00031] Avg episode reward: [(0, '21.924')]
436
+ [2025-03-20 23:26:42,059][00209] Updated weights for policy 0, policy_version 810 (0.0023)
437
+ [2025-03-20 23:26:46,191][00031] Fps is (10 sec: 8192.0, 60 sec: 8328.5, 300 sec: 8261.4). Total num frames: 3350528. Throughput: 0: 2086.7. Samples: 833218. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
438
+ [2025-03-20 23:26:46,193][00031] Avg episode reward: [(0, '19.798')]
439
+ [2025-03-20 23:26:47,073][00209] Updated weights for policy 0, policy_version 820 (0.0021)
440
+ [2025-03-20 23:26:51,192][00031] Fps is (10 sec: 8192.5, 60 sec: 8328.5, 300 sec: 8261.4). Total num frames: 3391488. Throughput: 0: 2090.5. Samples: 845960. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
441
+ [2025-03-20 23:26:51,196][00031] Avg episode reward: [(0, '19.309')]
442
+ [2025-03-20 23:26:51,770][00209] Updated weights for policy 0, policy_version 830 (0.0019)
443
+ [2025-03-20 23:26:56,191][00031] Fps is (10 sec: 8601.6, 60 sec: 8396.8, 300 sec: 8303.1). Total num frames: 3436544. Throughput: 0: 2102.4. Samples: 858940. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
444
+ [2025-03-20 23:26:56,193][00031] Avg episode reward: [(0, '21.041')]
445
+ [2025-03-20 23:26:56,530][00209] Updated weights for policy 0, policy_version 840 (0.0020)
446
+ [2025-03-20 23:27:01,192][00031] Fps is (10 sec: 8601.8, 60 sec: 8396.8, 300 sec: 8289.2). Total num frames: 3477504. Throughput: 0: 2107.6. Samples: 865430. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
447
+ [2025-03-20 23:27:01,193][00031] Avg episode reward: [(0, '24.327')]
448
+ [2025-03-20 23:27:01,203][00196] Saving new best policy, reward=24.327!
449
+ [2025-03-20 23:27:01,392][00209] Updated weights for policy 0, policy_version 850 (0.0017)
450
+ [2025-03-20 23:27:06,192][00031] Fps is (10 sec: 8191.3, 60 sec: 8396.7, 300 sec: 8289.2). Total num frames: 3518464. Throughput: 0: 2101.7. Samples: 877764. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
451
+ [2025-03-20 23:27:06,196][00031] Avg episode reward: [(0, '23.305')]
452
+ [2025-03-20 23:27:06,279][00209] Updated weights for policy 0, policy_version 860 (0.0017)
453
+ [2025-03-20 23:27:11,018][00209] Updated weights for policy 0, policy_version 870 (0.0015)
454
+ [2025-03-20 23:27:11,192][00031] Fps is (10 sec: 8601.6, 60 sec: 8465.1, 300 sec: 8303.1). Total num frames: 3563520. Throughput: 0: 2111.5. Samples: 890700. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
455
+ [2025-03-20 23:27:11,193][00031] Avg episode reward: [(0, '22.360')]
456
+ [2025-03-20 23:27:15,804][00209] Updated weights for policy 0, policy_version 880 (0.0016)
457
+ [2025-03-20 23:27:16,192][00031] Fps is (10 sec: 8601.5, 60 sec: 8396.7, 300 sec: 8289.2). Total num frames: 3604480. Throughput: 0: 2112.9. Samples: 897176. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0)
458
+ [2025-03-20 23:27:16,194][00031] Avg episode reward: [(0, '23.056')]
459
+ [2025-03-20 23:27:20,605][00209] Updated weights for policy 0, policy_version 890 (0.0020)
460
+ [2025-03-20 23:27:21,192][00031] Fps is (10 sec: 8601.2, 60 sec: 8465.0, 300 sec: 8303.1). Total num frames: 3649536. Throughput: 0: 2116.6. Samples: 910010. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
461
+ [2025-03-20 23:27:21,196][00031] Avg episode reward: [(0, '22.613')]
462
+ [2025-03-20 23:27:25,479][00209] Updated weights for policy 0, policy_version 900 (0.0020)
463
+ [2025-03-20 23:27:26,191][00031] Fps is (10 sec: 8602.4, 60 sec: 8465.1, 300 sec: 8303.1). Total num frames: 3690496. Throughput: 0: 2123.2. Samples: 922590. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
464
+ [2025-03-20 23:27:26,193][00031] Avg episode reward: [(0, '22.965')]
465
+ [2025-03-20 23:27:30,271][00209] Updated weights for policy 0, policy_version 910 (0.0020)
466
+ [2025-03-20 23:27:31,192][00031] Fps is (10 sec: 8192.4, 60 sec: 8396.8, 300 sec: 8317.0). Total num frames: 3731456. Throughput: 0: 2127.2. Samples: 928940. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
467
+ [2025-03-20 23:27:31,193][00031] Avg episode reward: [(0, '24.297')]
468
+ [2025-03-20 23:27:31,237][00196] Saving /kaggle/working/train_dir/default_experiment/checkpoint_p0/checkpoint_000000912_3735552.pth...
469
+ [2025-03-20 23:27:31,322][00196] Removing /kaggle/working/train_dir/default_experiment/checkpoint_p0/checkpoint_000000427_1748992.pth
470
+ [2025-03-20 23:27:35,093][00209] Updated weights for policy 0, policy_version 920 (0.0021)
471
+ [2025-03-20 23:27:36,192][00031] Fps is (10 sec: 8601.1, 60 sec: 8465.0, 300 sec: 8316.9). Total num frames: 3776512. Throughput: 0: 2128.2. Samples: 941728. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
472
+ [2025-03-20 23:27:36,194][00031] Avg episode reward: [(0, '25.425')]
473
+ [2025-03-20 23:27:36,195][00196] Saving new best policy, reward=25.425!
474
+ [2025-03-20 23:27:39,817][00209] Updated weights for policy 0, policy_version 930 (0.0019)
475
+ [2025-03-20 23:27:41,192][00031] Fps is (10 sec: 8601.6, 60 sec: 8465.2, 300 sec: 8317.0). Total num frames: 3817472. Throughput: 0: 2127.6. Samples: 954682. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
476
+ [2025-03-20 23:27:41,195][00031] Avg episode reward: [(0, '22.033')]
477
+ [2025-03-20 23:27:44,639][00209] Updated weights for policy 0, policy_version 940 (0.0019)
478
+ [2025-03-20 23:27:46,192][00031] Fps is (10 sec: 8602.1, 60 sec: 8533.3, 300 sec: 8317.0). Total num frames: 3862528. Throughput: 0: 2124.6. Samples: 961036. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
479
+ [2025-03-20 23:27:46,194][00031] Avg episode reward: [(0, '20.078')]
480
+ [2025-03-20 23:27:49,426][00209] Updated weights for policy 0, policy_version 950 (0.0019)
481
+ [2025-03-20 23:27:51,192][00031] Fps is (10 sec: 8601.4, 60 sec: 8533.3, 300 sec: 8317.0). Total num frames: 3903488. Throughput: 0: 2132.5. Samples: 973726. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
482
+ [2025-03-20 23:27:51,193][00031] Avg episode reward: [(0, '20.908')]
483
+ [2025-03-20 23:27:54,319][00209] Updated weights for policy 0, policy_version 960 (0.0016)
484
+ [2025-03-20 23:27:56,191][00031] Fps is (10 sec: 8192.0, 60 sec: 8465.1, 300 sec: 8303.1). Total num frames: 3944448. Throughput: 0: 2130.8. Samples: 986588. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
485
+ [2025-03-20 23:27:56,193][00031] Avg episode reward: [(0, '20.571')]
486
+ [2025-03-20 23:27:58,948][00209] Updated weights for policy 0, policy_version 970 (0.0023)
487
+ [2025-03-20 23:28:01,192][00031] Fps is (10 sec: 8601.8, 60 sec: 8533.3, 300 sec: 8330.8). Total num frames: 3989504. Throughput: 0: 2133.2. Samples: 993166. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
488
+ [2025-03-20 23:28:01,196][00031] Avg episode reward: [(0, '20.051')]
489
+ [2025-03-20 23:28:02,703][00196] Stopping Batcher_0...
490
+ [2025-03-20 23:28:02,704][00031] Component Batcher_0 stopped!
491
+ [2025-03-20 23:28:02,703][00196] Saving /kaggle/working/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth...
492
+ [2025-03-20 23:28:02,704][00196] Loop batcher_evt_loop terminating...
493
+ [2025-03-20 23:28:02,742][00209] Weights refcount: 2 0
494
+ [2025-03-20 23:28:02,744][00209] Stopping InferenceWorker_p0-w0...
495
+ [2025-03-20 23:28:02,745][00209] Loop inference_proc0-0_evt_loop terminating...
496
+ [2025-03-20 23:28:02,744][00031] Component InferenceWorker_p0-w0 stopped!
497
+ [2025-03-20 23:28:02,789][00196] Removing /kaggle/working/train_dir/default_experiment/checkpoint_p0/checkpoint_000000665_2723840.pth
498
+ [2025-03-20 23:28:02,805][00196] Saving /kaggle/working/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth...
499
+ [2025-03-20 23:28:02,832][00031] Component RolloutWorker_w1 stopped!
500
+ [2025-03-20 23:28:02,831][00211] Stopping RolloutWorker_w1...
501
+ [2025-03-20 23:28:02,836][00211] Loop rollout_proc1_evt_loop terminating...
502
+ [2025-03-20 23:28:02,843][00217] Stopping RolloutWorker_w6...
503
+ [2025-03-20 23:28:02,843][00031] Component RolloutWorker_w5 stopped!
504
+ [2025-03-20 23:28:02,844][00217] Loop rollout_proc6_evt_loop terminating...
505
+ [2025-03-20 23:28:02,845][00031] Component RolloutWorker_w6 stopped!
506
+ [2025-03-20 23:28:02,847][00213] Stopping RolloutWorker_w2...
507
+ [2025-03-20 23:28:02,848][00031] Component RolloutWorker_w2 stopped!
508
+ [2025-03-20 23:28:02,848][00213] Loop rollout_proc2_evt_loop terminating...
509
+ [2025-03-20 23:28:02,849][00216] Stopping RolloutWorker_w5...
510
+ [2025-03-20 23:28:02,850][00216] Loop rollout_proc5_evt_loop terminating...
511
+ [2025-03-20 23:28:02,936][00196] Stopping LearnerWorker_p0...
512
+ [2025-03-20 23:28:02,937][00196] Loop learner_proc0_evt_loop terminating...
513
+ [2025-03-20 23:28:02,937][00031] Component LearnerWorker_p0 stopped!
514
+ [2025-03-20 23:28:03,002][00212] Stopping RolloutWorker_w3...
515
+ [2025-03-20 23:28:03,004][00212] Loop rollout_proc3_evt_loop terminating...
516
+ [2025-03-20 23:28:03,003][00031] Component RolloutWorker_w3 stopped!
517
+ [2025-03-20 23:28:03,036][00215] Stopping RolloutWorker_w7...
518
+ [2025-03-20 23:28:03,036][00031] Component RolloutWorker_w7 stopped!
519
+ [2025-03-20 23:28:03,040][00215] Loop rollout_proc7_evt_loop terminating...
520
+ [2025-03-20 23:28:03,064][00214] Stopping RolloutWorker_w4...
521
+ [2025-03-20 23:28:03,064][00031] Component RolloutWorker_w4 stopped!
522
+ [2025-03-20 23:28:03,065][00214] Loop rollout_proc4_evt_loop terminating...
523
+ [2025-03-20 23:28:03,110][00031] Component RolloutWorker_w0 stopped!
524
+ [2025-03-20 23:28:03,111][00031] Waiting for process learner_proc0 to stop...
525
+ [2025-03-20 23:28:03,115][00210] Stopping RolloutWorker_w0...
526
+ [2025-03-20 23:28:03,116][00210] Loop rollout_proc0_evt_loop terminating...
527
+ [2025-03-20 23:28:04,424][00031] Waiting for process inference_proc0-0 to join...
528
+ [2025-03-20 23:28:04,426][00031] Waiting for process rollout_proc0 to join...
529
+ [2025-03-20 23:28:05,065][00031] Waiting for process rollout_proc1 to join...
530
+ [2025-03-20 23:28:05,066][00031] Waiting for process rollout_proc2 to join...
531
+ [2025-03-20 23:28:05,067][00031] Waiting for process rollout_proc3 to join...
532
+ [2025-03-20 23:28:05,069][00031] Waiting for process rollout_proc4 to join...
533
+ [2025-03-20 23:28:05,070][00031] Waiting for process rollout_proc5 to join...
534
+ [2025-03-20 23:28:05,071][00031] Waiting for process rollout_proc6 to join...
535
+ [2025-03-20 23:28:05,072][00031] Waiting for process rollout_proc7 to join...
536
+ [2025-03-20 23:28:05,073][00031] Batcher 0 profile tree view:
537
+ batching: 20.5565, releasing_batches: 0.0308
538
+ [2025-03-20 23:28:05,074][00031] InferenceWorker_p0-w0 profile tree view:
539
+ wait_policy: 0.0000
540
+ wait_policy_total: 16.8101
541
+ update_model: 7.0893
542
+ weight_update: 0.0022
543
+ one_step: 0.0049
544
+ handle_policy_step: 440.8086
545
+ deserialize: 13.3972, stack: 2.7370, obs_to_device_normalize: 106.3461, forward: 213.4394, send_messages: 23.2578
546
+ prepare_outputs: 59.6279
547
+ to_cpu: 37.1364
548
+ [2025-03-20 23:28:05,075][00031] Learner 0 profile tree view:
549
+ misc: 0.0058, prepare_batch: 13.1576
550
+ train: 54.6013
551
+ epoch_init: 0.0063, minibatch_init: 0.0076, losses_postprocess: 0.5497, kl_divergence: 0.5537, after_optimizer: 24.3350
552
+ calculate_losses: 18.1266
553
+ losses_init: 0.0041, forward_head: 1.1958, bptt_initial: 12.4322, tail: 0.7509, advantages_returns: 0.1977, losses: 1.8577
554
+ bptt: 1.4476
555
+ bptt_forward_core: 1.3815
556
+ update: 10.5385
557
+ clip: 0.9506
558
+ [2025-03-20 23:28:05,076][00031] RolloutWorker_w0 profile tree view:
559
+ wait_for_trajectories: 0.1884, enqueue_policy_requests: 8.6902, env_step: 363.3161, overhead: 7.5452, complete_rollouts: 1.3680
560
+ save_policy_outputs: 10.8651
561
+ split_output_tensors: 4.3671
562
+ [2025-03-20 23:28:05,077][00031] RolloutWorker_w7 profile tree view:
563
+ wait_for_trajectories: 0.1955, enqueue_policy_requests: 9.0198, env_step: 360.0656, overhead: 7.9315, complete_rollouts: 1.4588
564
+ save_policy_outputs: 11.3441
565
+ split_output_tensors: 4.6434
566
+ [2025-03-20 23:28:05,078][00031] Loop Runner_EvtLoop terminating...
567
+ [2025-03-20 23:28:05,079][00031] Runner profile tree view:
568
+ main_loop: 508.0986
569
+ [2025-03-20 23:28:05,080][00031] Collected {0: 4005888}, FPS: 7884.1
570
+ [2025-03-20 23:35:04,949][00031] Loading existing experiment configuration from /kaggle/working/train_dir/default_experiment/config.json
571
+ [2025-03-20 23:35:04,950][00031] Overriding arg 'num_workers' with value 1 passed from command line
572
+ [2025-03-20 23:35:04,951][00031] Adding new argument 'no_render'=True that is not in the saved config file!
573
+ [2025-03-20 23:35:04,952][00031] Adding new argument 'save_video'=True that is not in the saved config file!
574
+ [2025-03-20 23:35:04,953][00031] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file!
575
+ [2025-03-20 23:35:04,954][00031] Adding new argument 'video_name'=None that is not in the saved config file!
576
+ [2025-03-20 23:35:04,954][00031] Adding new argument 'max_num_frames'=1000000000.0 that is not in the saved config file!
577
+ [2025-03-20 23:35:04,955][00031] Adding new argument 'max_num_episodes'=10 that is not in the saved config file!
578
+ [2025-03-20 23:35:04,957][00031] Adding new argument 'push_to_hub'=False that is not in the saved config file!
579
+ [2025-03-20 23:35:04,958][00031] Adding new argument 'hf_repository'=None that is not in the saved config file!
580
+ [2025-03-20 23:35:04,959][00031] Adding new argument 'policy_index'=0 that is not in the saved config file!
581
+ [2025-03-20 23:35:04,960][00031] Adding new argument 'eval_deterministic'=False that is not in the saved config file!
582
+ [2025-03-20 23:35:04,961][00031] Adding new argument 'train_script'=None that is not in the saved config file!
583
+ [2025-03-20 23:35:04,962][00031] Adding new argument 'enjoy_script'=None that is not in the saved config file!
584
+ [2025-03-20 23:35:04,963][00031] Using frameskip 1 and render_action_repeat=4 for evaluation
585
+ [2025-03-20 23:35:04,995][00031] Doom resolution: 160x120, resize resolution: (128, 72)
586
+ [2025-03-20 23:35:04,998][00031] RunningMeanStd input shape: (3, 72, 128)
587
+ [2025-03-20 23:35:05,000][00031] RunningMeanStd input shape: (1,)
588
+ [2025-03-20 23:35:05,015][00031] ConvEncoder: input_channels=3
589
+ [2025-03-20 23:35:05,128][00031] Conv encoder output size: 512
590
+ [2025-03-20 23:35:05,129][00031] Policy head output size: 512
591
+ [2025-03-20 23:35:05,354][00031] Loading state from checkpoint /kaggle/working/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth...
592
+ [2025-03-20 23:35:06,191][00031] Num frames 100...
593
+ [2025-03-20 23:35:06,313][00031] Num frames 200...
594
+ [2025-03-20 23:35:06,441][00031] Num frames 300...
595
+ [2025-03-20 23:35:06,560][00031] Num frames 400...
596
+ [2025-03-20 23:35:06,681][00031] Num frames 500...
597
+ [2025-03-20 23:35:06,801][00031] Num frames 600...
598
+ [2025-03-20 23:35:06,925][00031] Num frames 700...
599
+ [2025-03-20 23:35:07,052][00031] Num frames 800...
600
+ [2025-03-20 23:35:07,175][00031] Num frames 900...
601
+ [2025-03-20 23:35:07,233][00031] Avg episode rewards: #0: 20.020, true rewards: #0: 9.020
602
+ [2025-03-20 23:35:07,234][00031] Avg episode reward: 20.020, avg true_objective: 9.020
603
+ [2025-03-20 23:35:07,356][00031] Num frames 1000...
604
+ [2025-03-20 23:35:07,483][00031] Num frames 1100...
605
+ [2025-03-20 23:35:07,607][00031] Num frames 1200...
606
+ [2025-03-20 23:35:07,732][00031] Num frames 1300...
607
+ [2025-03-20 23:35:07,853][00031] Num frames 1400...
608
+ [2025-03-20 23:35:07,979][00031] Num frames 1500...
609
+ [2025-03-20 23:35:08,111][00031] Num frames 1600...
610
+ [2025-03-20 23:35:08,255][00031] Avg episode rewards: #0: 17.850, true rewards: #0: 8.350
611
+ [2025-03-20 23:35:08,256][00031] Avg episode reward: 17.850, avg true_objective: 8.350
612
+ [2025-03-20 23:35:08,292][00031] Num frames 1700...
613
+ [2025-03-20 23:35:08,412][00031] Num frames 1800...
614
+ [2025-03-20 23:35:08,532][00031] Num frames 1900...
615
+ [2025-03-20 23:35:08,617][00031] Avg episode rewards: #0: 12.753, true rewards: #0: 6.420
616
+ [2025-03-20 23:35:08,618][00031] Avg episode reward: 12.753, avg true_objective: 6.420
617
+ [2025-03-20 23:35:08,707][00031] Num frames 2000...
618
+ [2025-03-20 23:35:08,832][00031] Num frames 2100...
619
+ [2025-03-20 23:35:08,956][00031] Num frames 2200...
620
+ [2025-03-20 23:35:09,089][00031] Num frames 2300...
621
+ [2025-03-20 23:35:09,217][00031] Num frames 2400...
622
+ [2025-03-20 23:35:09,342][00031] Num frames 2500...
623
+ [2025-03-20 23:35:09,470][00031] Num frames 2600...
624
+ [2025-03-20 23:35:09,592][00031] Num frames 2700...
625
+ [2025-03-20 23:35:09,717][00031] Num frames 2800...
626
+ [2025-03-20 23:35:09,844][00031] Num frames 2900...
627
+ [2025-03-20 23:35:09,971][00031] Num frames 3000...
628
+ [2025-03-20 23:35:10,096][00031] Num frames 3100...
629
+ [2025-03-20 23:35:10,217][00031] Num frames 3200...
630
+ [2025-03-20 23:35:10,350][00031] Num frames 3300...
631
+ [2025-03-20 23:35:10,449][00031] Avg episode rewards: #0: 16.835, true rewards: #0: 8.335
632
+ [2025-03-20 23:35:10,450][00031] Avg episode reward: 16.835, avg true_objective: 8.335
633
+ [2025-03-20 23:35:10,532][00031] Num frames 3400...
634
+ [2025-03-20 23:35:10,656][00031] Num frames 3500...
635
+ [2025-03-20 23:35:10,782][00031] Num frames 3600...
636
+ [2025-03-20 23:35:10,913][00031] Num frames 3700...
637
+ [2025-03-20 23:35:11,073][00031] Avg episode rewards: #0: 14.564, true rewards: #0: 7.564
638
+ [2025-03-20 23:35:11,074][00031] Avg episode reward: 14.564, avg true_objective: 7.564
639
+ [2025-03-20 23:35:11,096][00031] Num frames 3800...
640
+ [2025-03-20 23:35:11,218][00031] Num frames 3900...
641
+ [2025-03-20 23:35:11,343][00031] Num frames 4000...
642
+ [2025-03-20 23:35:11,468][00031] Num frames 4100...
643
+ [2025-03-20 23:35:11,592][00031] Num frames 4200...
644
+ [2025-03-20 23:35:11,716][00031] Num frames 4300...
645
+ [2025-03-20 23:35:11,882][00031] Avg episode rewards: #0: 13.650, true rewards: #0: 7.317
646
+ [2025-03-20 23:35:11,884][00031] Avg episode reward: 13.650, avg true_objective: 7.317
647
+ [2025-03-20 23:35:11,897][00031] Num frames 4400...
648
+ [2025-03-20 23:35:12,017][00031] Num frames 4500...
649
+ [2025-03-20 23:35:12,153][00031] Num frames 4600...
650
+ [2025-03-20 23:35:12,283][00031] Num frames 4700...
651
+ [2025-03-20 23:35:12,410][00031] Num frames 4800...
652
+ [2025-03-20 23:35:12,537][00031] Num frames 4900...
653
+ [2025-03-20 23:35:12,665][00031] Num frames 5000...
654
+ [2025-03-20 23:35:12,787][00031] Num frames 5100...
655
+ [2025-03-20 23:35:12,912][00031] Num frames 5200...
656
+ [2025-03-20 23:35:13,037][00031] Num frames 5300...
657
+ [2025-03-20 23:35:13,157][00031] Num frames 5400...
658
+ [2025-03-20 23:35:13,281][00031] Num frames 5500...
659
+ [2025-03-20 23:35:13,409][00031] Num frames 5600...
660
+ [2025-03-20 23:35:13,538][00031] Num frames 5700...
661
+ [2025-03-20 23:35:13,716][00031] Avg episode rewards: #0: 15.709, true rewards: #0: 8.280
662
+ [2025-03-20 23:35:13,717][00031] Avg episode reward: 15.709, avg true_objective: 8.280
663
+ [2025-03-20 23:35:13,726][00031] Num frames 5800...
664
+ [2025-03-20 23:35:13,856][00031] Num frames 5900...
665
+ [2025-03-20 23:35:14,007][00031] Num frames 6000...
666
+ [2025-03-20 23:35:14,133][00031] Num frames 6100...
667
+ [2025-03-20 23:35:14,259][00031] Num frames 6200...
668
+ [2025-03-20 23:35:14,385][00031] Num frames 6300...
669
+ [2025-03-20 23:35:14,517][00031] Num frames 6400...
670
+ [2025-03-20 23:35:14,647][00031] Num frames 6500...
671
+ [2025-03-20 23:35:14,781][00031] Num frames 6600...
672
+ [2025-03-20 23:35:14,909][00031] Num frames 6700...
673
+ [2025-03-20 23:35:15,036][00031] Num frames 6800...
674
+ [2025-03-20 23:35:15,154][00031] Num frames 6900...
675
+ [2025-03-20 23:35:15,317][00031] Avg episode rewards: #0: 17.364, true rewards: #0: 8.739
676
+ [2025-03-20 23:35:15,318][00031] Avg episode reward: 17.364, avg true_objective: 8.739
677
+ [2025-03-20 23:35:15,330][00031] Num frames 7000...
678
+ [2025-03-20 23:35:15,450][00031] Num frames 7100...
679
+ [2025-03-20 23:35:15,568][00031] Num frames 7200...
680
+ [2025-03-20 23:35:15,697][00031] Num frames 7300...
681
+ [2025-03-20 23:35:15,820][00031] Num frames 7400...
682
+ [2025-03-20 23:35:15,946][00031] Num frames 7500...
683
+ [2025-03-20 23:35:16,073][00031] Num frames 7600...
684
+ [2025-03-20 23:35:16,194][00031] Num frames 7700...
685
+ [2025-03-20 23:35:16,309][00031] Num frames 7800...
686
+ [2025-03-20 23:35:16,434][00031] Num frames 7900...
687
+ [2025-03-20 23:35:16,559][00031] Num frames 8000...
688
+ [2025-03-20 23:35:16,684][00031] Num frames 8100...
689
+ [2025-03-20 23:35:16,753][00031] Avg episode rewards: #0: 17.901, true rewards: #0: 9.012
690
+ [2025-03-20 23:35:16,753][00031] Avg episode reward: 17.901, avg true_objective: 9.012
691
+ [2025-03-20 23:35:16,863][00031] Num frames 8200...
692
+ [2025-03-20 23:35:16,995][00031] Num frames 8300...
693
+ [2025-03-20 23:35:17,124][00031] Num frames 8400...
694
+ [2025-03-20 23:35:17,250][00031] Num frames 8500...
695
+ [2025-03-20 23:35:17,380][00031] Num frames 8600...
696
+ [2025-03-20 23:35:17,512][00031] Num frames 8700...
697
+ [2025-03-20 23:35:17,634][00031] Num frames 8800...
698
+ [2025-03-20 23:35:17,757][00031] Num frames 8900...
699
+ [2025-03-20 23:35:17,882][00031] Num frames 9000...
700
+ [2025-03-20 23:35:18,007][00031] Num frames 9100...
701
+ [2025-03-20 23:35:18,127][00031] Num frames 9200...
702
+ [2025-03-20 23:35:18,246][00031] Num frames 9300...
703
+ [2025-03-20 23:35:18,364][00031] Num frames 9400...
704
+ [2025-03-20 23:35:18,486][00031] Num frames 9500...
705
+ [2025-03-20 23:35:18,609][00031] Num frames 9600...
706
+ [2025-03-20 23:35:18,741][00031] Num frames 9700...
707
+ [2025-03-20 23:35:18,865][00031] Num frames 9800...
708
+ [2025-03-20 23:35:18,984][00031] Num frames 9900...
709
+ [2025-03-20 23:35:19,110][00031] Num frames 10000...
710
+ [2025-03-20 23:35:19,239][00031] Num frames 10100...
711
+ [2025-03-20 23:35:19,371][00031] Num frames 10200...
712
+ [2025-03-20 23:35:19,442][00031] Avg episode rewards: #0: 21.711, true rewards: #0: 10.211
713
+ [2025-03-20 23:35:19,443][00031] Avg episode reward: 21.711, avg true_objective: 10.211
714
+ [2025-03-20 23:35:55,955][00031] Replay video saved to /kaggle/working/train_dir/default_experiment/replay.mp4!
715
+ [2025-03-20 23:37:41,964][00031] Loading existing experiment configuration from /kaggle/working/train_dir/default_experiment/config.json
716
+ [2025-03-20 23:37:41,966][00031] Overriding arg 'num_workers' with value 1 passed from command line
717
+ [2025-03-20 23:37:41,967][00031] Adding new argument 'no_render'=True that is not in the saved config file!
718
+ [2025-03-20 23:37:41,968][00031] Adding new argument 'save_video'=True that is not in the saved config file!
719
+ [2025-03-20 23:37:41,969][00031] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file!
720
+ [2025-03-20 23:37:41,970][00031] Adding new argument 'video_name'=None that is not in the saved config file!
721
+ [2025-03-20 23:37:41,972][00031] Adding new argument 'max_num_frames'=100000 that is not in the saved config file!
722
+ [2025-03-20 23:37:41,973][00031] Adding new argument 'max_num_episodes'=10 that is not in the saved config file!
723
+ [2025-03-20 23:37:41,973][00031] Adding new argument 'push_to_hub'=True that is not in the saved config file!
724
+ [2025-03-20 23:37:41,974][00031] Adding new argument 'hf_repository'='salym/rl_course_vizdoom_health_gathering_supreme' that is not in the saved config file!
725
+ [2025-03-20 23:37:41,975][00031] Adding new argument 'policy_index'=0 that is not in the saved config file!
726
+ [2025-03-20 23:37:41,976][00031] Adding new argument 'eval_deterministic'=False that is not in the saved config file!
727
+ [2025-03-20 23:37:41,978][00031] Adding new argument 'train_script'=None that is not in the saved config file!
728
+ [2025-03-20 23:37:41,978][00031] Adding new argument 'enjoy_script'=None that is not in the saved config file!
729
+ [2025-03-20 23:37:41,979][00031] Using frameskip 1 and render_action_repeat=4 for evaluation
730
+ [2025-03-20 23:37:42,004][00031] RunningMeanStd input shape: (3, 72, 128)
731
+ [2025-03-20 23:37:42,006][00031] RunningMeanStd input shape: (1,)
732
+ [2025-03-20 23:37:42,018][00031] ConvEncoder: input_channels=3
733
+ [2025-03-20 23:37:42,059][00031] Conv encoder output size: 512
734
+ [2025-03-20 23:37:42,060][00031] Policy head output size: 512
735
+ [2025-03-20 23:37:42,078][00031] Loading state from checkpoint /kaggle/working/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth...
736
+ [2025-03-20 23:37:42,554][00031] Num frames 100...
737
+ [2025-03-20 23:37:42,679][00031] Num frames 200...
738
+ [2025-03-20 23:37:42,803][00031] Num frames 300...
739
+ [2025-03-20 23:37:42,934][00031] Num frames 400...
740
+ [2025-03-20 23:37:43,056][00031] Num frames 500...
741
+ [2025-03-20 23:37:43,178][00031] Num frames 600...
742
+ [2025-03-20 23:37:43,299][00031] Num frames 700...
743
+ [2025-03-20 23:37:43,423][00031] Num frames 800...
744
+ [2025-03-20 23:37:43,546][00031] Num frames 900...
745
+ [2025-03-20 23:37:43,664][00031] Num frames 1000...
746
+ [2025-03-20 23:37:43,807][00031] Num frames 1100...
747
+ [2025-03-20 23:37:43,942][00031] Num frames 1200...
748
+ [2025-03-20 23:37:44,091][00031] Num frames 1300...
749
+ [2025-03-20 23:37:44,220][00031] Num frames 1400...
750
+ [2025-03-20 23:37:44,343][00031] Num frames 1500...
751
+ [2025-03-20 23:37:44,403][00031] Avg episode rewards: #0: 39.040, true rewards: #0: 15.040
752
+ [2025-03-20 23:37:44,404][00031] Avg episode reward: 39.040, avg true_objective: 15.040
753
+ [2025-03-20 23:37:44,524][00031] Num frames 1600...
754
+ [2025-03-20 23:37:44,656][00031] Num frames 1700...
755
+ [2025-03-20 23:37:44,785][00031] Num frames 1800...
756
+ [2025-03-20 23:37:44,914][00031] Num frames 1900...
757
+ [2025-03-20 23:37:45,073][00031] Avg episode rewards: #0: 23.420, true rewards: #0: 9.920
758
+ [2025-03-20 23:37:45,074][00031] Avg episode reward: 23.420, avg true_objective: 9.920
759
+ [2025-03-20 23:37:45,095][00031] Num frames 2000...
760
+ [2025-03-20 23:37:45,213][00031] Num frames 2100...
761
+ [2025-03-20 23:37:45,335][00031] Num frames 2200...
762
+ [2025-03-20 23:37:45,457][00031] Num frames 2300...
763
+ [2025-03-20 23:37:45,574][00031] Num frames 2400...
764
+ [2025-03-20 23:37:45,693][00031] Num frames 2500...
765
+ [2025-03-20 23:37:45,814][00031] Num frames 2600...
766
+ [2025-03-20 23:37:45,943][00031] Num frames 2700...
767
+ [2025-03-20 23:37:46,072][00031] Num frames 2800...
768
+ [2025-03-20 23:37:46,202][00031] Num frames 2900...
769
+ [2025-03-20 23:37:46,365][00031] Avg episode rewards: #0: 23.610, true rewards: #0: 9.943
770
+ [2025-03-20 23:37:46,366][00031] Avg episode reward: 23.610, avg true_objective: 9.943
771
+ [2025-03-20 23:37:46,389][00031] Num frames 3000...
772
+ [2025-03-20 23:37:46,515][00031] Num frames 3100...
773
+ [2025-03-20 23:37:46,641][00031] Num frames 3200...
774
+ [2025-03-20 23:37:46,766][00031] Num frames 3300...
775
+ [2025-03-20 23:37:46,894][00031] Num frames 3400...
776
+ [2025-03-20 23:37:47,033][00031] Avg episode rewards: #0: 20.158, true rewards: #0: 8.657
777
+ [2025-03-20 23:37:47,034][00031] Avg episode reward: 20.158, avg true_objective: 8.657
778
+ [2025-03-20 23:37:47,083][00031] Num frames 3500...
779
+ [2025-03-20 23:37:47,207][00031] Num frames 3600...
780
+ [2025-03-20 23:37:47,330][00031] Num frames 3700...
781
+ [2025-03-20 23:37:47,461][00031] Num frames 3800...
782
+ [2025-03-20 23:37:47,587][00031] Num frames 3900...
783
+ [2025-03-20 23:37:47,714][00031] Num frames 4000...
784
+ [2025-03-20 23:37:47,840][00031] Num frames 4100...
785
+ [2025-03-20 23:37:47,967][00031] Num frames 4200...
786
+ [2025-03-20 23:37:48,091][00031] Num frames 4300...
787
+ [2025-03-20 23:37:48,213][00031] Num frames 4400...
788
+ [2025-03-20 23:37:48,333][00031] Num frames 4500...
789
+ [2025-03-20 23:37:48,456][00031] Num frames 4600...
790
+ [2025-03-20 23:37:48,528][00031] Avg episode rewards: #0: 20.630, true rewards: #0: 9.230
791
+ [2025-03-20 23:37:48,529][00031] Avg episode reward: 20.630, avg true_objective: 9.230
792
+ [2025-03-20 23:37:48,631][00031] Num frames 4700...
793
+ [2025-03-20 23:37:48,769][00031] Num frames 4800...
794
+ [2025-03-20 23:37:48,898][00031] Num frames 4900...
795
+ [2025-03-20 23:37:49,020][00031] Num frames 5000...
796
+ [2025-03-20 23:37:49,142][00031] Num frames 5100...
797
+ [2025-03-20 23:37:49,261][00031] Num frames 5200...
798
+ [2025-03-20 23:37:49,387][00031] Num frames 5300...
799
+ [2025-03-20 23:37:49,513][00031] Num frames 5400...
800
+ [2025-03-20 23:37:49,643][00031] Num frames 5500...
801
+ [2025-03-20 23:37:49,760][00031] Num frames 5600...
802
+ [2025-03-20 23:37:49,886][00031] Num frames 5700...
803
+ [2025-03-20 23:37:50,009][00031] Num frames 5800...
804
+ [2025-03-20 23:37:50,085][00031] Avg episode rewards: #0: 21.695, true rewards: #0: 9.695
805
+ [2025-03-20 23:37:50,087][00031] Avg episode reward: 21.695, avg true_objective: 9.695
806
+ [2025-03-20 23:37:50,185][00031] Num frames 5900...
807
+ [2025-03-20 23:37:50,312][00031] Num frames 6000...
808
+ [2025-03-20 23:37:50,440][00031] Num frames 6100...
809
+ [2025-03-20 23:37:50,563][00031] Num frames 6200...
810
+ [2025-03-20 23:37:50,620][00031] Avg episode rewards: #0: 19.573, true rewards: #0: 8.859
811
+ [2025-03-20 23:37:50,622][00031] Avg episode reward: 19.573, avg true_objective: 8.859
812
+ [2025-03-20 23:37:50,757][00031] Num frames 6300...
813
+ [2025-03-20 23:37:50,896][00031] Num frames 6400...
814
+ [2025-03-20 23:37:51,028][00031] Num frames 6500...
815
+ [2025-03-20 23:37:51,155][00031] Num frames 6600...
816
+ [2025-03-20 23:37:51,283][00031] Num frames 6700...
817
+ [2025-03-20 23:37:51,411][00031] Num frames 6800...
818
+ [2025-03-20 23:37:51,536][00031] Num frames 6900...
819
+ [2025-03-20 23:37:51,655][00031] Num frames 7000...
820
+ [2025-03-20 23:37:51,781][00031] Num frames 7100...
821
+ [2025-03-20 23:37:51,913][00031] Num frames 7200...
822
+ [2025-03-20 23:37:52,021][00031] Avg episode rewards: #0: 20.555, true rewards: #0: 9.055
823
+ [2025-03-20 23:37:52,022][00031] Avg episode reward: 20.555, avg true_objective: 9.055
824
+ [2025-03-20 23:37:52,090][00031] Num frames 7300...
825
+ [2025-03-20 23:37:52,207][00031] Num frames 7400...
826
+ [2025-03-20 23:37:52,323][00031] Num frames 7500...
827
+ [2025-03-20 23:37:52,443][00031] Num frames 7600...
828
+ [2025-03-20 23:37:52,566][00031] Num frames 7700...
829
+ [2025-03-20 23:37:52,643][00031] Avg episode rewards: #0: 19.575, true rewards: #0: 8.574
830
+ [2025-03-20 23:37:52,644][00031] Avg episode reward: 19.575, avg true_objective: 8.574
831
+ [2025-03-20 23:37:52,748][00031] Num frames 7800...
832
+ [2025-03-20 23:37:52,874][00031] Num frames 7900...
833
+ [2025-03-20 23:37:52,995][00031] Num frames 8000...
834
+ [2025-03-20 23:37:53,130][00031] Num frames 8100...
835
+ [2025-03-20 23:37:53,253][00031] Num frames 8200...
836
+ [2025-03-20 23:37:53,426][00031] Avg episode rewards: #0: 18.693, true rewards: #0: 8.293
837
+ [2025-03-20 23:37:53,427][00031] Avg episode reward: 18.693, avg true_objective: 8.293
838
+ [2025-03-20 23:38:23,118][00031] Replay video saved to /kaggle/working/train_dir/default_experiment/replay.mp4!