{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 3.2298195362091064, "min": 3.2068076133728027, "max": 3.295711040496826, "count": 54 }, "SoccerTwos.Policy.Entropy.sum": { "value": 58291.78125, "min": 30495.3046875, "max": 124481.7734375, "count": 54 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 999.0, "min": 440.1818181818182, "max": 999.0, "count": 54 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19980.0, "min": 4388.0, "max": 29824.0, "count": 54 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1185.7329534832095, "min": 1185.7329534832095, "max": 1201.9676610588351, "count": 49 }, "SoccerTwos.Self-play.ELO.sum": { "value": 4742.931813932838, "min": 2373.6295313696746, "max": 16695.78597867757, "count": 49 }, "SoccerTwos.Step.mean": { "value": 539560.0, "min": 9722.0, "max": 539560.0, "count": 54 }, "SoccerTwos.Step.sum": { "value": 539560.0, "min": 9722.0, "max": 539560.0, "count": 54 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.012044129893183708, "min": -0.06829550117254257, "max": 0.0005884378915652633, "count": 54 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -0.12044130265712738, "min": -1.161023497581482, "max": 0.007649692706763744, "count": 54 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.011996770277619362, "min": -0.06828037649393082, "max": -0.0006331371841952205, "count": 54 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -0.11996770650148392, "min": -1.1607487201690674, "max": -0.0082307830452919, "count": 54 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 54 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 54 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": 0.0, "min": -0.5714285714285714, "max": 0.3844249974936247, "count": 54 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 0.0, "min": -8.0, "max": 6.150799959897995, "count": 54 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.0, "min": -0.5714285714285714, "max": 0.3844249974936247, "count": 54 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 0.0, "min": -8.0, "max": 6.150799959897995, "count": 54 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 54 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 54 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.015840340607489147, "min": 0.013639200828038156, "max": 0.02040239532337485, "count": 24 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.015840340607489147, "min": 0.013639200828038156, "max": 0.02040239532337485, "count": 24 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.0016526828073741247, "min": 0.0003451225345391625, "max": 0.0050576629117131235, "count": 24 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.0016526828073741247, "min": 0.0003451225345391625, "max": 0.0050576629117131235, "count": 24 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.0016475419125830135, "min": 0.00034673779761457504, "max": 0.005173764664990207, "count": 24 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.0016475419125830135, "min": 0.00034673779761457504, "max": 0.005173764664990207, "count": 24 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 24 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 24 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.19999999999999996, "max": 0.20000000000000007, "count": 24 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.19999999999999996, "max": 0.20000000000000007, "count": 24 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 24 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 24 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1692566715", "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [GCC 11.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.x86_64 --run-id=SoccerTwos --no-graphics", "mlagents_version": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.11.0+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1692567901" }, "total": 1186.796577056, "count": 1, "self": 0.448078885999621, "children": { "run_training.setup": { "total": 0.06522621600015555, "count": 1, "self": 0.06522621600015555 }, "TrainerController.start_learning": { "total": 1186.2832719540002, "count": 1, "self": 0.8209160919629994, "children": { "TrainerController._reset_env": { "total": 4.875695208000025, "count": 3, "self": 4.875695208000025 }, "TrainerController.advance": { "total": 1180.584005204037, "count": 35237, "self": 0.8505803110344914, "children": { "env_step": { "total": 945.9641394549751, "count": 35237, "self": 750.3498611599937, "children": { "SubprocessEnvManager._take_step": { "total": 195.1073614079853, "count": 35237, "self": 5.8479826399914145, "children": { "TorchPolicy.evaluate": { "total": 189.2593787679939, "count": 69938, "self": 189.2593787679939 } } }, "workers": { "total": 0.5069168869961231, "count": 35236, "self": 0.0, "children": { "worker_root": { "total": 1184.254714291997, "count": 35236, "is_parallel": true, "self": 545.7972143160148, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.008556542999940575, "count": 2, "is_parallel": true, "self": 0.0047986139995828125, "children": { "_process_rank_one_or_two_observation": { "total": 0.0037579290003577626, "count": 8, "is_parallel": true, "self": 0.0037579290003577626 } } }, "UnityEnvironment.step": { "total": 0.04336083099997268, "count": 1, "is_parallel": true, "self": 0.0012058040001647896, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0008507229999850097, "count": 1, "is_parallel": true, "self": 0.0008507229999850097 }, "communicator.exchange": { "total": 0.037376435999931346, "count": 1, "is_parallel": true, "self": 0.037376435999931346 }, "steps_from_proto": { "total": 0.003927867999891532, "count": 2, "is_parallel": true, "self": 0.0006559480000305484, "children": { "_process_rank_one_or_two_observation": { "total": 0.003271919999860984, "count": 8, "is_parallel": true, "self": 0.003271919999860984 } } } } } } }, "UnityEnvironment.step": { "total": 638.4516568929814, "count": 35235, "is_parallel": true, "self": 39.71773754907804, "children": { "UnityEnvironment._generate_step_input": { "total": 25.09644600000979, "count": 35235, "is_parallel": true, "self": 25.09644600000979 }, "communicator.exchange": { "total": 444.22516056995414, "count": 35235, "is_parallel": true, "self": 444.22516056995414 }, "steps_from_proto": { "total": 129.41231277393945, "count": 70470, "is_parallel": true, "self": 20.99869423675318, "children": { "_process_rank_one_or_two_observation": { "total": 108.41361853718627, "count": 281880, "is_parallel": true, "self": 108.41361853718627 } } } } }, "steps_from_proto": { "total": 0.005843083000854676, "count": 4, "is_parallel": true, "self": 0.0011706020004567108, "children": { "_process_rank_one_or_two_observation": { "total": 0.0046724810003979655, "count": 16, "is_parallel": true, "self": 0.0046724810003979655 } } } } } } } } }, "trainer_advance": { "total": 233.7692854380275, "count": 35236, "self": 8.112916358028542, "children": { "process_trajectory": { "total": 59.526320617998635, "count": 35236, "self": 59.283857597998804, "children": { "RLTrainer._checkpoint": { "total": 0.24246301999983189, "count": 1, "self": 0.24246301999983189 } } }, "_update_policy": { "total": 166.13004846200033, "count": 24, "self": 107.08406202099991, "children": { "TorchPOCAOptimizer.update": { "total": 59.04598644100042, "count": 732, "self": 59.04598644100042 } } } } } } }, "trainer_threads": { "total": 1.1880001693498343e-06, "count": 1, "self": 1.1880001693498343e-06 }, "TrainerController._save_models": { "total": 0.00265426199985086, "count": 1, "self": 4.6055999973759754e-05, "children": { "RLTrainer._checkpoint": { "total": 0.0026082059998771, "count": 1, "self": 0.0026082059998771 } } } } } } }