{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 2.895887851715088, "min": 2.882753849029541, "max": 3.295729160308838, "count": 226 }, "SoccerTwos.Policy.Entropy.sum": { "value": 57454.4140625, "min": 25651.0703125, "max": 105463.2890625, "count": 226 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 146.83333333333334, "min": 105.3695652173913, "max": 999.0, "count": 226 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 21144.0, "min": 12844.0, "max": 28068.0, "count": 226 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1316.8759414108188, "min": 1198.1496415677789, "max": 1319.7872740790808, "count": 219 }, "SoccerTwos.Self-play.ELO.sum": { "value": 94815.06778157895, "min": 2400.1128337129485, "max": 121098.57561141098, "count": 219 }, "SoccerTwos.Step.mean": { "value": 2259678.0, "min": 9050.0, "max": 2259678.0, "count": 226 }, "SoccerTwos.Step.sum": { "value": 2259678.0, "min": 9050.0, "max": 2259678.0, "count": 226 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": 0.07486466318368912, "min": -0.07765861600637436, "max": 0.11771281063556671, "count": 226 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": 5.3153910636901855, "min": -2.096782684326172, "max": 7.782065391540527, "count": 226 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": 0.07389528304338455, "min": -0.07905006408691406, "max": 0.12164086103439331, "count": 226 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": 5.246565341949463, "min": -2.1343517303466797, "max": 7.895816802978516, "count": 226 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 226 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 226 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": 0.016436619657865713, "min": -0.7077000001445413, "max": 0.5363320775751798, "count": 226 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 1.1669999957084656, "min": -16.336400032043457, "max": 28.425600111484528, "count": 226 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.016436619657865713, "min": -0.7077000001445413, "max": 0.5363320775751798, "count": 226 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 1.1669999957084656, "min": -16.336400032043457, "max": 28.425600111484528, "count": 226 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 226 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 226 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.016837426551501267, "min": 0.01198086826504247, "max": 0.024409048135081927, "count": 106 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.016837426551501267, "min": 0.01198086826504247, "max": 0.024409048135081927, "count": 106 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.03583123578379552, "min": 0.00015843015717109665, "max": 0.04081849145392577, "count": 106 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.03583123578379552, "min": 0.00015843015717109665, "max": 0.04081849145392577, "count": 106 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.036340306202570595, "min": 0.00016699927970572996, "max": 0.04152804675201575, "count": 106 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.036340306202570595, "min": 0.00016699927970572996, "max": 0.04152804675201575, "count": 106 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 106 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 106 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 106 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 106 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 106 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 106 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1735163089", "python_version": "3.10.12 (main, Jul 5 2023, 15:34:07) [Clang 14.0.6 ]", "command_line_arguments": "/usr/local/anaconda3/envs/rl/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos.app --run-id=SoccerTwos --no-graphics", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.2.2", "numpy_version": "1.23.5", "end_time_seconds": "1735172997" }, "total": 9908.326268667006, "count": 1, "self": 0.416268749977462, "children": { "run_training.setup": { "total": 0.030486042029224336, "count": 1, "self": 0.030486042029224336 }, "TrainerController.start_learning": { "total": 9907.879513875, "count": 1, "self": 1.8073161386419088, "children": { "TrainerController._reset_env": { "total": 3.9221587099600583, "count": 12, "self": 3.9221587099600583 }, "TrainerController.advance": { "total": 9902.007278526435, "count": 146925, "self": 1.6621134666493163, "children": { "env_step": { "total": 7814.5486751960125, "count": 146925, "self": 7559.627500034054, "children": { "SubprocessEnvManager._take_step": { "total": 253.58589280885644, "count": 146925, "self": 8.642564501496963, "children": { "TorchPolicy.evaluate": { "total": 244.94332830735948, "count": 289916, "self": 244.94332830735948 } } }, "workers": { "total": 1.3352823531022295, "count": 146924, "self": 0.0, "children": { "worker_root": { "total": 9902.382326544495, "count": 146924, "is_parallel": true, "self": 2541.4676400698954, "children": { "steps_from_proto": { "total": 0.020308081060647964, "count": 24, "is_parallel": true, "self": 0.002620324376039207, "children": { "_process_rank_one_or_two_observation": { "total": 0.017687756684608757, "count": 96, "is_parallel": true, "self": 0.017687756684608757 } } }, "UnityEnvironment.step": { "total": 7360.894378393539, "count": 146924, "is_parallel": true, "self": 18.734035621280782, "children": { "UnityEnvironment._generate_step_input": { "total": 123.97077023831662, "count": 146924, "is_parallel": true, "self": 123.97077023831662 }, "communicator.exchange": { "total": 6978.391198601341, "count": 146924, "is_parallel": true, "self": 6978.391198601341 }, "steps_from_proto": { "total": 239.79837393260095, "count": 293848, "is_parallel": true, "self": 28.120688659138978, "children": { "_process_rank_one_or_two_observation": { "total": 211.67768527346198, "count": 1175392, "is_parallel": true, "self": 211.67768527346198 } } } } } } } } } } }, "trainer_advance": { "total": 2085.796489863773, "count": 146924, "self": 14.571734376833774, "children": { "process_trajectory": { "total": 277.76263502566144, "count": 146924, "self": 277.1710022756597, "children": { "RLTrainer._checkpoint": { "total": 0.591632750001736, "count": 4, "self": 0.591632750001736 } } }, "_update_policy": { "total": 1793.4621204612777, "count": 106, "self": 173.52280944015365, "children": { "TorchPOCAOptimizer.update": { "total": 1619.939311021124, "count": 3180, "self": 1619.939311021124 } } } } } } }, "trainer_threads": { "total": 6.670597940683365e-07, "count": 1, "self": 6.670597940683365e-07 }, "TrainerController._save_models": { "total": 0.14275983290281147, "count": 1, "self": 0.0012041248846799135, "children": { "RLTrainer._checkpoint": { "total": 0.14155570801813155, "count": 1, "self": 0.14155570801813155 } } } } } } }