{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 3.2846975326538086, "min": 3.283822774887085, "max": 3.2954800128936768, "count": 400 }, "SoccerTwos.Policy.Entropy.sum": { "value": 37209.0546875, "min": 5367.615234375, "max": 95567.234375, "count": 400 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 834.6666666666666, "min": 120.0, "max": 999.0, "count": 395 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 10016.0, "min": 480.0, "max": 21912.0, "count": 395 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1196.9844288272664, "min": 1186.8514244750104, "max": 1203.6963913824627, "count": 295 }, "SoccerTwos.Self-play.ELO.sum": { "value": 2393.9688576545327, "min": 2373.702848950021, "max": 16689.968268214398, "count": 295 }, "SoccerTwos.Step.mean": { "value": 1999688.0, "min": 4786.0, "max": 1999688.0, "count": 400 }, "SoccerTwos.Step.sum": { "value": 1999688.0, "min": 4786.0, "max": 1999688.0, "count": 400 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.0032570294570177794, "min": -0.18008702993392944, "max": 0.017847955226898193, "count": 400 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -0.03908435255289078, "min": -2.3411314487457275, "max": 0.2855672836303711, "count": 400 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.0027322948444634676, "min": -0.22792373597621918, "max": 0.021335411816835403, "count": 400 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -0.032787539064884186, "min": -2.9630086421966553, "max": 0.34136658906936646, "count": 400 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 395 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 395 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": 0.16433333357175192, "min": -1.0, "max": 0.7052000164985657, "count": 395 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 0.9860000014305115, "min": -10.0, "max": 5.293600051663816, "count": 395 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.16433333357175192, "min": -1.0, "max": 0.7052000164985657, "count": 395 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 0.9860000014305115, "min": -10.0, "max": 5.293600051663816, "count": 395 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 400 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 400 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.016190374735742807, "min": 0.0025480178301222622, "max": 0.026732152793556452, "count": 185 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.016190374735742807, "min": 0.0025480178301222622, "max": 0.026732152793556452, "count": 185 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.003027775906957686, "min": 1.7174223557958612e-05, "max": 0.012865165481343865, "count": 185 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.003027775906957686, "min": 1.7174223557958612e-05, "max": 0.012865165481343865, "count": 185 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.0030372627661563456, "min": 1.88395115401363e-05, "max": 0.010008264798671007, "count": 185 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.0030372627661563456, "min": 1.88395115401363e-05, "max": 0.010008264798671007, "count": 185 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 1.4069985940000186e-07, "min": 1.4069985940000186e-07, "max": 9.948660051340001e-05, "count": 185 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 1.4069985940000186e-07, "min": 1.4069985940000186e-07, "max": 9.948660051340001e-05, "count": 185 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.10014060000000001, "min": 0.10014060000000001, "max": 0.19948660000000001, "count": 185 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.10014060000000001, "min": 0.10014060000000001, "max": 0.19948660000000001, "count": 185 }, "SoccerTwos.Policy.Beta.mean": { "value": 1.7015940000000092e-05, "min": 1.7015940000000092e-05, "max": 0.00497438134, "count": 185 }, "SoccerTwos.Policy.Beta.sum": { "value": 1.7015940000000092e-05, "min": 1.7015940000000092e-05, "max": 0.00497438134, "count": 185 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1741220577", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training/SoccerTwos.x86_64 --run-id=SnowballTarget1 --no-graphics --force", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.6.0+cu124", "numpy_version": "1.23.5", "end_time_seconds": "1741224674" }, "total": 4096.737163092, "count": 1, "self": 0.42513011200026085, "children": { "run_training.setup": { "total": 0.020172583999965354, "count": 1, "self": 0.020172583999965354 }, "TrainerController.start_learning": { "total": 4096.291860396, "count": 1, "self": 2.9763582920468252, "children": { "TrainerController._reset_env": { "total": 3.046322120000468, "count": 20, "self": 3.046322120000468 }, "TrainerController.advance": { "total": 4090.1615792109524, "count": 130397, "self": 3.0497762756776865, "children": { "env_step": { "total": 3563.3522551272017, "count": 130397, "self": 2613.88380928328, "children": { "SubprocessEnvManager._take_step": { "total": 947.7815389719092, "count": 130397, "self": 19.88158878482909, "children": { "TorchPolicy.evaluate": { "total": 927.8999501870801, "count": 258740, "self": 927.8999501870801 } } }, "workers": { "total": 1.6869068720127416, "count": 130397, "self": 0.0, "children": { "worker_root": { "total": 4088.2957167451286, "count": 130397, "is_parallel": true, "self": 1882.7282312380507, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0031447860001208028, "count": 2, "is_parallel": true, "self": 0.0008647729996482667, "children": { "_process_rank_one_or_two_observation": { "total": 0.002280013000472536, "count": 8, "is_parallel": true, "self": 0.002280013000472536 } } }, "UnityEnvironment.step": { "total": 0.04133039600014854, "count": 1, "is_parallel": true, "self": 0.0010966590002681187, "children": { "UnityEnvironment._generate_step_input": { "total": 0.000860708999880444, "count": 1, "is_parallel": true, "self": 0.000860708999880444 }, "communicator.exchange": { "total": 0.03435367600013706, "count": 1, "is_parallel": true, "self": 0.03435367600013706 }, "steps_from_proto": { "total": 0.00501935199986292, "count": 2, "is_parallel": true, "self": 0.0005738400000154797, "children": { "_process_rank_one_or_two_observation": { "total": 0.00444551199984744, "count": 8, "is_parallel": true, "self": 0.00444551199984744 } } } } } } }, "UnityEnvironment.step": { "total": 2205.5237438550785, "count": 130396, "is_parallel": true, "self": 134.7243621562925, "children": { "UnityEnvironment._generate_step_input": { "total": 94.29759519295135, "count": 130396, "is_parallel": true, "self": 94.29759519295135 }, "communicator.exchange": { "total": 1544.8969947429207, "count": 130396, "is_parallel": true, "self": 1544.8969947429207 }, "steps_from_proto": { "total": 431.6047917629139, "count": 260792, "is_parallel": true, "self": 70.97741628397625, "children": { "_process_rank_one_or_two_observation": { "total": 360.62737547893767, "count": 1043168, "is_parallel": true, "self": 360.62737547893767 } } } } }, "steps_from_proto": { "total": 0.04374165199942581, "count": 38, "is_parallel": true, "self": 0.008970732998022868, "children": { "_process_rank_one_or_two_observation": { "total": 0.034770919001402945, "count": 152, "is_parallel": true, "self": 0.034770919001402945 } } } } } } } } }, "trainer_advance": { "total": 523.7595478080727, "count": 130397, "self": 25.63806918502587, "children": { "process_trajectory": { "total": 215.63743091304627, "count": 130397, "self": 215.16179785004647, "children": { "RLTrainer._checkpoint": { "total": 0.4756330629998047, "count": 4, "self": 0.4756330629998047 } } }, "_update_policy": { "total": 282.4840477100006, "count": 185, "self": 193.157638445992, "children": { "TorchPOCAOptimizer.update": { "total": 89.32640926400859, "count": 746, "self": 89.32640926400859 } } } } } } }, "trainer_threads": { "total": 9.109999155043624e-07, "count": 1, "self": 9.109999155043624e-07 }, "TrainerController._save_models": { "total": 0.10759986199991545, "count": 1, "self": 0.0011934329995710868, "children": { "RLTrainer._checkpoint": { "total": 0.10640642900034436, "count": 1, "self": 0.10640642900034436 } } } } } } }