{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.4987492561340332, "min": 1.4687831401824951, "max": 3.295746088027954, "count": 1415 }, "SoccerTwos.Policy.Entropy.sum": { "value": 30790.3046875, "min": 18622.8828125, "max": 108499.0546875, "count": 1415 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 45.632075471698116, "min": 40.98275862068966, "max": 999.0, "count": 1415 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19348.0, "min": 16092.0, "max": 26748.0, "count": 1415 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1666.6848612477863, "min": 1198.862184640307, "max": 1732.9687814775837, "count": 1408 }, "SoccerTwos.Self-play.ELO.sum": { "value": 353337.1905845307, "min": 2400.0217860570974, "max": 388621.78174823633, "count": 1408 }, "SoccerTwos.Step.mean": { "value": 14149970.0, "min": 9394.0, "max": 14149970.0, "count": 1415 }, "SoccerTwos.Step.sum": { "value": 14149970.0, "min": 9394.0, "max": 14149970.0, "count": 1415 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.042452745139598846, "min": -0.15603262186050415, "max": 0.16966989636421204, "count": 1415 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -9.042434692382812, "min": -24.17540168762207, "max": 25.75534439086914, "count": 1415 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.04572370648384094, "min": -0.15828919410705566, "max": 0.16486148536205292, "count": 1415 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -9.73914909362793, "min": -24.06298065185547, "max": 25.919845581054688, "count": 1415 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 1415 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 1415 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.12937652616993361, "min": -0.5138800024986268, "max": 0.5900315720784036, "count": 1415 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -27.557200074195862, "min": -74.71399998664856, "max": 51.5206001996994, "count": 1415 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.12937652616993361, "min": -0.5138800024986268, "max": 0.5900315720784036, "count": 1415 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -27.557200074195862, "min": -74.71399998664856, "max": 51.5206001996994, "count": 1415 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 1415 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 1415 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.01879771878690614, "min": 0.009975290037497567, "max": 0.026518385223365235, "count": 684 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.01879771878690614, "min": 0.009975290037497567, "max": 0.026518385223365235, "count": 684 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.11922327304879825, "min": 1.9979877803658987e-05, "max": 0.1255020409822464, "count": 684 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.11922327304879825, "min": 1.9979877803658987e-05, "max": 0.1255020409822464, "count": 684 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.12138473739226659, "min": 1.988412389740309e-05, "max": 0.1276343566675981, "count": 684 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.12138473739226659, "min": 1.988412389740309e-05, "max": 0.1276343566675981, "count": 684 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 684 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 684 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.2, "max": 0.20000000000000007, "count": 684 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.2, "max": 0.20000000000000007, "count": 684 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 684 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 684 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1696475516", "python_version": "3.9.18 (main, Sep 11 2023, 08:25:10) \n[Clang 14.0.6 ]", "command_line_arguments": "/opt/homebrew/Caskroom/miniconda/base/envs/hf-rl/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos.app --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", "numpy_version": "1.21.2", "end_time_seconds": "1696520939" }, "total": 45423.014969375, "count": 1, "self": 0.18460329099616501, "children": { "run_training.setup": { "total": 0.01175666700000022, "count": 1, "self": 0.01175666700000022 }, "TrainerController.start_learning": { "total": 45422.818609417, "count": 1, "self": 10.917374800090329, "children": { "TrainerController._reset_env": { "total": 4.425894872005513, "count": 71, "self": 4.425894872005513 }, "TrainerController.advance": { "total": 45407.38982716191, "count": 976178, "self": 9.960945893602911, "children": { "env_step": { "total": 35121.811429669804, "count": 976178, "self": 33645.357237809425, "children": { "SubprocessEnvManager._take_step": { "total": 1469.4130961211345, "count": 976178, "self": 41.28506463991266, "children": { "TorchPolicy.evaluate": { "total": 1428.1280314812218, "count": 1779816, "self": 1428.1280314812218 } } }, "workers": { "total": 7.041095739245463, "count": 976178, "self": 0.0, "children": { "worker_root": { "total": 45395.48765676783, "count": 976178, "is_parallel": true, "self": 13065.285799928712, "children": { "steps_from_proto": { "total": 0.08380895602536742, "count": 142, "is_parallel": true, "self": 0.011396127006569223, "children": { "_process_rank_one_or_two_observation": { "total": 0.0724128290187982, "count": 568, "is_parallel": true, "self": 0.0724128290187982 } } }, "UnityEnvironment.step": { "total": 32330.118047883094, "count": 976178, "is_parallel": true, "self": 94.98763262297507, "children": { "UnityEnvironment._generate_step_input": { "total": 508.84762762833793, "count": 976178, "is_parallel": true, "self": 508.84762762833793 }, "communicator.exchange": { "total": 30659.478355265474, "count": 976178, "is_parallel": true, "self": 30659.478355265474 }, "steps_from_proto": { "total": 1066.8044323663082, "count": 1952356, "is_parallel": true, "self": 140.81307109628915, "children": { "_process_rank_one_or_two_observation": { "total": 925.9913612700191, "count": 7809424, "is_parallel": true, "self": 925.9913612700191 } } } } } } } } } } }, "trainer_advance": { "total": 10275.617451598508, "count": 976178, "self": 80.53959470139307, "children": { "process_trajectory": { "total": 2434.5386137400783, "count": 976178, "self": 2432.297959696082, "children": { "RLTrainer._checkpoint": { "total": 2.2406540439960736, "count": 28, "self": 2.2406540439960736 } } }, "_update_policy": { "total": 7760.539243157037, "count": 685, "self": 1073.6516661982896, "children": { "TorchPOCAOptimizer.update": { "total": 6686.887576958748, "count": 20547, "self": 6686.887576958748 } } } } } } }, "trainer_threads": { "total": 4.999965312890708e-07, "count": 1, "self": 4.999965312890708e-07 }, "TrainerController._save_models": { "total": 0.08551208299468271, "count": 1, "self": 0.0014863329924992286, "children": { "RLTrainer._checkpoint": { "total": 0.08402575000218349, "count": 1, "self": 0.08402575000218349 } } } } } } }