|
{ |
|
"name": "root", |
|
"gauges": { |
|
"SoccerTwos.Policy.Entropy.mean": { |
|
"value": 1.8434988260269165, |
|
"min": 1.8346599340438843, |
|
"max": 3.2956979274749756, |
|
"count": 862 |
|
}, |
|
"SoccerTwos.Policy.Entropy.sum": { |
|
"value": 36928.96875, |
|
"min": 4740.29248046875, |
|
"max": 150987.234375, |
|
"count": 862 |
|
}, |
|
"SoccerTwos.Environment.EpisodeLength.mean": { |
|
"value": 47.98, |
|
"min": 43.309734513274336, |
|
"max": 999.0, |
|
"count": 862 |
|
}, |
|
"SoccerTwos.Environment.EpisodeLength.sum": { |
|
"value": 19192.0, |
|
"min": 11996.0, |
|
"max": 28644.0, |
|
"count": 862 |
|
}, |
|
"SoccerTwos.Self-play.ELO.mean": { |
|
"value": 1566.773003609935, |
|
"min": 1173.1243076122191, |
|
"max": 1582.0444014461386, |
|
"count": 797 |
|
}, |
|
"SoccerTwos.Self-play.ELO.sum": { |
|
"value": 313354.60072198696, |
|
"min": 2348.198127248749, |
|
"max": 334040.74287821946, |
|
"count": 797 |
|
}, |
|
"SoccerTwos.Step.mean": { |
|
"value": 8619858.0, |
|
"min": 9342.0, |
|
"max": 8619858.0, |
|
"count": 862 |
|
}, |
|
"SoccerTwos.Step.sum": { |
|
"value": 8619858.0, |
|
"min": 9342.0, |
|
"max": 8619858.0, |
|
"count": 862 |
|
}, |
|
"SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { |
|
"value": 0.018008800223469734, |
|
"min": -0.12056028097867966, |
|
"max": 0.22568106651306152, |
|
"count": 862 |
|
}, |
|
"SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { |
|
"value": 3.601759910583496, |
|
"min": -19.651325225830078, |
|
"max": 34.01498031616211, |
|
"count": 862 |
|
}, |
|
"SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { |
|
"value": 0.016617776826024055, |
|
"min": -0.1251881718635559, |
|
"max": 0.22502605617046356, |
|
"count": 862 |
|
}, |
|
"SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { |
|
"value": 3.3235554695129395, |
|
"min": -20.405672073364258, |
|
"max": 35.035430908203125, |
|
"count": 862 |
|
}, |
|
"SoccerTwos.Environment.CumulativeReward.mean": { |
|
"value": 0.0, |
|
"min": 0.0, |
|
"max": 0.0, |
|
"count": 862 |
|
}, |
|
"SoccerTwos.Environment.CumulativeReward.sum": { |
|
"value": 0.0, |
|
"min": 0.0, |
|
"max": 0.0, |
|
"count": 862 |
|
}, |
|
"SoccerTwos.Policy.ExtrinsicReward.mean": { |
|
"value": 0.05361400067806244, |
|
"min": -0.6412761892591204, |
|
"max": 0.4861466586589813, |
|
"count": 862 |
|
}, |
|
"SoccerTwos.Policy.ExtrinsicReward.sum": { |
|
"value": 10.722800135612488, |
|
"min": -67.88499993085861, |
|
"max": 74.02039980888367, |
|
"count": 862 |
|
}, |
|
"SoccerTwos.Environment.GroupCumulativeReward.mean": { |
|
"value": 0.05361400067806244, |
|
"min": -0.6412761892591204, |
|
"max": 0.4861466586589813, |
|
"count": 862 |
|
}, |
|
"SoccerTwos.Environment.GroupCumulativeReward.sum": { |
|
"value": 10.722800135612488, |
|
"min": -67.88499993085861, |
|
"max": 74.02039980888367, |
|
"count": 862 |
|
}, |
|
"SoccerTwos.IsTraining.mean": { |
|
"value": 1.0, |
|
"min": 1.0, |
|
"max": 1.0, |
|
"count": 862 |
|
}, |
|
"SoccerTwos.IsTraining.sum": { |
|
"value": 1.0, |
|
"min": 1.0, |
|
"max": 1.0, |
|
"count": 862 |
|
}, |
|
"SoccerTwos.Losses.PolicyLoss.mean": { |
|
"value": 0.013608232833697305, |
|
"min": 0.010440699631969134, |
|
"max": 0.023799832879255214, |
|
"count": 409 |
|
}, |
|
"SoccerTwos.Losses.PolicyLoss.sum": { |
|
"value": 0.013608232833697305, |
|
"min": 0.010440699631969134, |
|
"max": 0.023799832879255214, |
|
"count": 409 |
|
}, |
|
"SoccerTwos.Losses.ValueLoss.mean": { |
|
"value": 0.10985415776570638, |
|
"min": 1.2019552552070914e-06, |
|
"max": 0.11892705634236336, |
|
"count": 409 |
|
}, |
|
"SoccerTwos.Losses.ValueLoss.sum": { |
|
"value": 0.10985415776570638, |
|
"min": 1.2019552552070914e-06, |
|
"max": 0.11892705634236336, |
|
"count": 409 |
|
}, |
|
"SoccerTwos.Losses.BaselineLoss.mean": { |
|
"value": 0.11099382241566975, |
|
"min": 1.1897383368856633e-06, |
|
"max": 0.12036320293943087, |
|
"count": 409 |
|
}, |
|
"SoccerTwos.Losses.BaselineLoss.sum": { |
|
"value": 0.11099382241566975, |
|
"min": 1.1897383368856633e-06, |
|
"max": 0.12036320293943087, |
|
"count": 409 |
|
}, |
|
"SoccerTwos.Policy.LearningRate.mean": { |
|
"value": 0.0003, |
|
"min": 0.0003, |
|
"max": 0.0003, |
|
"count": 409 |
|
}, |
|
"SoccerTwos.Policy.LearningRate.sum": { |
|
"value": 0.0003, |
|
"min": 0.0003, |
|
"max": 0.0003, |
|
"count": 409 |
|
}, |
|
"SoccerTwos.Policy.Epsilon.mean": { |
|
"value": 0.20000000000000007, |
|
"min": 0.20000000000000004, |
|
"max": 0.20000000000000007, |
|
"count": 409 |
|
}, |
|
"SoccerTwos.Policy.Epsilon.sum": { |
|
"value": 0.20000000000000007, |
|
"min": 0.20000000000000004, |
|
"max": 0.20000000000000007, |
|
"count": 409 |
|
}, |
|
"SoccerTwos.Policy.Beta.mean": { |
|
"value": 0.005000000000000001, |
|
"min": 0.005000000000000001, |
|
"max": 0.005000000000000001, |
|
"count": 409 |
|
}, |
|
"SoccerTwos.Policy.Beta.sum": { |
|
"value": 0.005000000000000001, |
|
"min": 0.005000000000000001, |
|
"max": 0.005000000000000001, |
|
"count": 409 |
|
} |
|
}, |
|
"metadata": { |
|
"timer_format_version": "0.1.0", |
|
"start_time_seconds": "1685874103", |
|
"python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \n[GCC 9.4.0]", |
|
"command_line_arguments": "/home/user/.virtualenvs/rl-course-unit7/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos.x86_64 --run-id=SoccerTwos --no-graphics --force", |
|
"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": "1685891765" |
|
}, |
|
"total": 17661.997806900006, |
|
"count": 1, |
|
"self": 0.3408695000252919, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.009274399999412708, |
|
"count": 1, |
|
"self": 0.009274399999412708 |
|
}, |
|
"TrainerController.start_learning": { |
|
"total": 17661.64766299998, |
|
"count": 1, |
|
"self": 13.799717194051482, |
|
"children": { |
|
"TrainerController._reset_env": { |
|
"total": 30.533092100100475, |
|
"count": 43, |
|
"self": 30.533092100100475 |
|
}, |
|
"TrainerController.advance": { |
|
"total": 17616.84690400584, |
|
"count": 579121, |
|
"self": 13.594753412296996, |
|
"children": { |
|
"env_step": { |
|
"total": 13016.45070159607, |
|
"count": 579121, |
|
"self": 7400.9529640890105, |
|
"children": { |
|
"SubprocessEnvManager._take_step": { |
|
"total": 5607.194474806223, |
|
"count": 579121, |
|
"self": 92.68533239483077, |
|
"children": { |
|
"TorchPolicy.evaluate": { |
|
"total": 5514.5091424113925, |
|
"count": 1095438, |
|
"self": 5514.5091424113925 |
|
} |
|
} |
|
}, |
|
"workers": { |
|
"total": 8.303262700836058, |
|
"count": 579121, |
|
"self": 0.0, |
|
"children": { |
|
"worker_root": { |
|
"total": 17632.79518169303, |
|
"count": 579121, |
|
"is_parallel": true, |
|
"self": 11662.593824684722, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.0, |
|
"count": 0, |
|
"is_parallel": true, |
|
"self": 0.0, |
|
"children": { |
|
"steps_from_proto": { |
|
"total": 0.013703799995710142, |
|
"count": 2, |
|
"is_parallel": true, |
|
"self": 0.00627020001411438, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.007433599981595762, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.007433599981595762 |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 0.19131019999622367, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.001357399974949658, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 0.04366450000088662, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.04366450000088662 |
|
}, |
|
"communicator.exchange": { |
|
"total": 0.14161740000417922, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.14161740000417922 |
|
}, |
|
"steps_from_proto": { |
|
"total": 0.004670900016208179, |
|
"count": 2, |
|
"is_parallel": true, |
|
"self": 0.0012376000377116725, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.003433299978496507, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.003433299978496507 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 5970.13942190817, |
|
"count": 579120, |
|
"is_parallel": true, |
|
"self": 295.2301604988461, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 208.11454050992324, |
|
"count": 579120, |
|
"is_parallel": true, |
|
"self": 208.11454050992324 |
|
}, |
|
"communicator.exchange": { |
|
"total": 4580.229337689278, |
|
"count": 579120, |
|
"is_parallel": true, |
|
"self": 4580.229337689278 |
|
}, |
|
"steps_from_proto": { |
|
"total": 886.5653832101234, |
|
"count": 1158240, |
|
"is_parallel": true, |
|
"self": 185.6499321908923, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 700.9154510192311, |
|
"count": 4632960, |
|
"is_parallel": true, |
|
"self": 700.9154510192311 |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"steps_from_proto": { |
|
"total": 0.06193510013690684, |
|
"count": 84, |
|
"is_parallel": true, |
|
"self": 0.013425699682557024, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.048509400454349816, |
|
"count": 336, |
|
"is_parallel": true, |
|
"self": 0.048509400454349816 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_advance": { |
|
"total": 4586.801448997474, |
|
"count": 579121, |
|
"self": 92.61359740051557, |
|
"children": { |
|
"process_trajectory": { |
|
"total": 2136.028718097048, |
|
"count": 579121, |
|
"self": 2128.789415196996, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 7.23930290005228, |
|
"count": 17, |
|
"self": 7.23930290005228 |
|
} |
|
} |
|
}, |
|
"_update_policy": { |
|
"total": 2358.1591334999102, |
|
"count": 409, |
|
"self": 1090.5400891008903, |
|
"children": { |
|
"TorchPOCAOptimizer.update": { |
|
"total": 1267.61904439902, |
|
"count": 12279, |
|
"self": 1267.61904439902 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_threads": { |
|
"total": 1.200009137392044e-06, |
|
"count": 1, |
|
"self": 1.200009137392044e-06 |
|
}, |
|
"TrainerController._save_models": { |
|
"total": 0.46794849997968413, |
|
"count": 1, |
|
"self": 0.013114499975927174, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.45483400000375696, |
|
"count": 1, |
|
"self": 0.45483400000375696 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |