{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 2.050253391265869, "min": 2.034529685974121, "max": 3.227118968963623, "count": 411 }, "SoccerTwos.Policy.Entropy.sum": { "value": 41661.1484375, "min": 19230.033203125, "max": 131912.359375, "count": 411 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 50.864583333333336, "min": 40.55833333333333, "max": 999.0, "count": 411 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19532.0, "min": 7992.0, "max": 26396.0, "count": 411 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1619.3064656883705, "min": 1206.3464324066229, "max": 1622.4247989601322, "count": 386 }, "SoccerTwos.Self-play.ELO.sum": { "value": 310906.8414121671, "min": 2412.6928648132457, "max": 376982.44280891324, "count": 386 }, "SoccerTwos.Step.mean": { "value": 4619976.0, "min": 519681.0, "max": 4619976.0, "count": 411 }, "SoccerTwos.Step.sum": { "value": 4619976.0, "min": 519681.0, "max": 4619976.0, "count": 411 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": 0.05835111811757088, "min": -0.08314729481935501, "max": 0.19273114204406738, "count": 411 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": 11.203414916992188, "min": -13.63615608215332, "max": 30.840782165527344, "count": 411 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": 0.0547499842941761, "min": -0.09096977114677429, "max": 0.19480246305465698, "count": 411 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": 10.51199722290039, "min": -14.919042587280273, "max": 30.88077163696289, "count": 411 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 411 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 411 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.0062666647136211395, "min": -0.7777777777777778, "max": 0.42301250124971074, "count": 411 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -1.2031996250152588, "min": -78.96480000019073, "max": 64.0497996211052, "count": 411 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.0062666647136211395, "min": -0.7777777777777778, "max": 0.42301250124971074, "count": 411 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -1.2031996250152588, "min": -78.96480000019073, "max": 64.0497996211052, "count": 411 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 411 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 411 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.015313063388263496, "min": 0.011214571007682632, "max": 0.023672397252327452, "count": 195 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.015313063388263496, "min": 0.011214571007682632, "max": 0.023672397252327452, "count": 195 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.10252293199300766, "min": 4.140989418980704e-06, "max": 0.11862916002670924, "count": 195 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.10252293199300766, "min": 4.140989418980704e-06, "max": 0.11862916002670924, "count": 195 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.10426674634218216, "min": 4.45966087833464e-06, "max": 0.121265010535717, "count": 195 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.10426674634218216, "min": 4.45966087833464e-06, "max": 0.121265010535717, "count": 195 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 195 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 195 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 195 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 195 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 195 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 195 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1690710715", "python_version": "3.9.17 (main, Jul 5 2023, 20:47:11) [MSC v.1916 64 bit (AMD64)]", "command_line_arguments": "\\\\?\\C:\\Users\\praty\\anaconda3\\envs\\rl\\Scripts\\mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.exe --run-id=SoccerTwos --no-graphics --resume", "mlagents_version": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.0.1+cpu", "numpy_version": "1.21.2", "end_time_seconds": "1690730866" }, "total": 20151.2319752, "count": 1, "self": 1.5930857000021206, "children": { "run_training.setup": { "total": 0.19156610000000018, "count": 1, "self": 0.19156610000000018 }, "TrainerController.start_learning": { "total": 20149.4473234, "count": 1, "self": 11.337723500910215, "children": { "TrainerController._reset_env": { "total": 7.253884600004711, "count": 22, "self": 7.253884600004711 }, "TrainerController.advance": { "total": 20130.55692599908, "count": 275875, "self": 11.953038298328465, "children": { "env_step": { "total": 8576.67303360019, "count": 275875, "self": 6783.355670400021, "children": { "SubprocessEnvManager._take_step": { "total": 1786.1429430003095, "count": 275875, "self": 69.90850140024281, "children": { "TorchPolicy.evaluate": { "total": 1716.2344416000667, "count": 522378, "self": 1716.2344416000667 } } }, "workers": { "total": 7.1744201998584725, "count": 275874, "self": 0.0, "children": { "worker_root": { "total": 20126.62331700034, "count": 275874, "is_parallel": true, "self": 14632.633021800773, "children": { "steps_from_proto": { "total": 0.06739730000300259, "count": 44, "is_parallel": true, "self": 0.013614499999679452, "children": { "_process_rank_one_or_two_observation": { "total": 0.05378280000332314, "count": 176, "is_parallel": true, "self": 0.05378280000332314 } } }, "UnityEnvironment.step": { "total": 5493.922897899563, "count": 275874, "is_parallel": true, "self": 283.60887699985415, "children": { "UnityEnvironment._generate_step_input": { "total": 202.12518460061193, "count": 275874, "is_parallel": true, "self": 202.12518460061193 }, "communicator.exchange": { "total": 4088.7022474993046, "count": 275874, "is_parallel": true, "self": 4088.7022474993046 }, "steps_from_proto": { "total": 919.4865887997933, "count": 551748, "is_parallel": true, "self": 182.57454560020005, "children": { "_process_rank_one_or_two_observation": { "total": 736.9120431995932, "count": 2206992, "is_parallel": true, "self": 736.9120431995932 } } } } } } } } } } }, "trainer_advance": { "total": 11541.930854100561, "count": 275874, "self": 74.77104820042223, "children": { "process_trajectory": { "total": 1665.2003485001283, "count": 275874, "self": 1663.0265831001298, "children": { "RLTrainer._checkpoint": { "total": 2.1737653999985014, "count": 8, "self": 2.1737653999985014 } } }, "_update_policy": { "total": 9801.959457400011, "count": 196, "self": 917.6712407999676, "children": { "TorchPOCAOptimizer.update": { "total": 8884.288216600044, "count": 5880, "self": 8884.288216600044 } } } } } } }, "trainer_threads": { "total": 3.4000004234258085e-06, "count": 1, "self": 3.4000004234258085e-06 }, "TrainerController._save_models": { "total": 0.29878590000225813, "count": 1, "self": 0.02720229999977164, "children": { "RLTrainer._checkpoint": { "total": 0.2715836000024865, "count": 1, "self": 0.2715836000024865 } } } } } } }