{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.8723636865615845, "min": 1.7541974782943726, "max": 3.2958028316497803, "count": 593 }, "SoccerTwos.Policy.Entropy.sum": { "value": 37986.515625, "min": 29945.1171875, "max": 112419.703125, "count": 593 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 49.857142857142854, "min": 40.78151260504202, "max": 999.0, "count": 593 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19544.0, "min": 16164.0, "max": 24272.0, "count": 593 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1602.0229134076994, "min": 1194.1664684268064, "max": 1632.8628018606792, "count": 590 }, "SoccerTwos.Self-play.ELO.sum": { "value": 313996.4910279091, "min": 2390.6186252188522, "max": 385269.0296528018, "count": 590 }, "SoccerTwos.Step.mean": { "value": 5929882.0, "min": 9152.0, "max": 5929882.0, "count": 593 }, "SoccerTwos.Step.sum": { "value": 5929882.0, "min": 9152.0, "max": 5929882.0, "count": 593 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.011386324651539326, "min": -0.07559556514024734, "max": 0.30134502053260803, "count": 593 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -2.243105888366699, "min": -14.816730499267578, "max": 38.11559295654297, "count": 593 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.0042584724724292755, "min": -0.08128456026315689, "max": 0.30652838945388794, "count": 593 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -0.8389191031455994, "min": -15.931774139404297, "max": 38.12245559692383, "count": 593 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 593 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 593 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.09663959535850486, "min": -0.6842105263157895, "max": 0.6156806474731814, "count": 593 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -19.038000285625458, "min": -54.18879997730255, "max": 79.10879975557327, "count": 593 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.09663959535850486, "min": -0.6842105263157895, "max": 0.6156806474731814, "count": 593 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -19.038000285625458, "min": -54.18879997730255, "max": 79.10879975557327, "count": 593 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 593 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 593 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.016978301322766735, "min": 0.011128998205337363, "max": 0.027278373801770308, "count": 286 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.016978301322766735, "min": 0.011128998205337363, "max": 0.027278373801770308, "count": 286 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.1125520331164201, "min": 0.0010447911180866262, "max": 0.12484250217676163, "count": 286 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.1125520331164201, "min": 0.0010447911180866262, "max": 0.12484250217676163, "count": 286 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.11449736927946409, "min": 0.001045413986624529, "max": 0.1277681755522887, "count": 286 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.11449736927946409, "min": 0.001045413986624529, "max": 0.1277681755522887, "count": 286 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.000291106187964605, "min": 0.000291106187964605, "max": 0.0002999604150131951, "count": 286 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.000291106187964605, "min": 0.000291106187964605, "max": 0.0002999604150131951, "count": 286 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.19703539500000006, "min": 0.19703539500000006, "max": 0.19998680500000002, "count": 286 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.19703539500000006, "min": 0.19703539500000006, "max": 0.19998680500000002, "count": 286 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.004852066210499999, "min": 0.004852066210499999, "max": 0.004999341569499999, "count": 286 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.004852066210499999, "min": 0.004852066210499999, "max": 0.004999341569499999, "count": 286 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1677938339", "python_version": "3.9.16 | packaged by conda-forge | (main, Feb 1 2023, 21:39:03) \n[GCC 11.3.0]", "command_line_arguments": "/opt/conda/envs/rl/bin/mlagents-learn ./ml-agents/config/poca/SoccerTwos.yaml --env ./ml-agents/training-envs-executables/Soccer/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": "1.8.1+cu111", "numpy_version": "1.21.2", "end_time_seconds": "1678014961" }, "total": 76621.71481010201, "count": 1, "self": 3.4311009410012048, "children": { "run_training.setup": { "total": 0.024470964999636635, "count": 1, "self": 0.024470964999636635 }, "TrainerController.start_learning": { "total": 76618.25923819601, "count": 1, "self": 10.956967044534395, "children": { "TrainerController._reset_env": { "total": 9.670278003031854, "count": 30, "self": 9.670278003031854 }, "TrainerController.advance": { "total": 76597.35695718948, "count": 408131, "self": 10.450964555231621, "children": { "env_step": { "total": 72966.26667078599, "count": 408131, "self": 70579.69719207654, "children": { "SubprocessEnvManager._take_step": { "total": 2379.6736674868444, "count": 408131, "self": 55.50945471189334, "children": { "TorchPolicy.evaluate": { "total": 2324.164212774951, "count": 748077, "self": 2324.164212774951 } } }, "workers": { "total": 6.895811222610064, "count": 408130, "self": 0.0, "children": { "worker_root": { "total": 76599.9000101015, "count": 408130, "is_parallel": true, "self": 7397.858097038319, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005997055995976552, "count": 2, "is_parallel": true, "self": 0.0008024279959499836, "children": { "_process_rank_one_or_two_observation": { "total": 0.005194628000026569, "count": 8, "is_parallel": true, "self": 0.005194628000026569 } } }, "UnityEnvironment.step": { "total": 0.21028139200643636, "count": 1, "is_parallel": true, "self": 0.0002831190067809075, "children": { "UnityEnvironment._generate_step_input": { "total": 0.006894007994560525, "count": 1, "is_parallel": true, "self": 0.006894007994560525 }, "communicator.exchange": { "total": 0.19763975898968056, "count": 1, "is_parallel": true, "self": 0.19763975898968056 }, "steps_from_proto": { "total": 0.005464506015414372, "count": 2, "is_parallel": true, "self": 0.0005729170516133308, "children": { "_process_rank_one_or_two_observation": { "total": 0.004891588963801041, "count": 8, "is_parallel": true, "self": 0.004891588963801041 } } } } } } }, "UnityEnvironment.step": { "total": 69201.88179623117, "count": 408129, "is_parallel": true, "self": 111.24734427715885, "children": { "UnityEnvironment._generate_step_input": { "total": 1150.8276157755463, "count": 408129, "is_parallel": true, "self": 1150.8276157755463 }, "communicator.exchange": { "total": 65827.53694993193, "count": 408129, "is_parallel": true, "self": 65827.53694993193 }, "steps_from_proto": { "total": 2112.269886246533, "count": 816258, "is_parallel": true, "self": 223.77512643302907, "children": { "_process_rank_one_or_two_observation": { "total": 1888.494759813504, "count": 3265032, "is_parallel": true, "self": 1888.494759813504 } } } } }, "steps_from_proto": { "total": 0.16011683200486004, "count": 58, "is_parallel": true, "self": 0.016931115242186934, "children": { "_process_rank_one_or_two_observation": { "total": 0.1431857167626731, "count": 232, "is_parallel": true, "self": 0.1431857167626731 } } } } } } } } }, "trainer_advance": { "total": 3620.6393218482553, "count": 408130, "self": 72.60683037881972, "children": { "process_trajectory": { "total": 1473.3965893133136, "count": 408130, "self": 1465.544722266408, "children": { "RLTrainer._checkpoint": { "total": 7.8518670469056815, "count": 11, "self": 7.8518670469056815 } } }, "_update_policy": { "total": 2074.635902156122, "count": 286, "self": 1596.4877418332326, "children": { "TorchPOCAOptimizer.update": { "total": 478.14816032288945, "count": 8586, "self": 478.14816032288945 } } } } } } }, "trainer_threads": { "total": 1.2280070222914219e-06, "count": 1, "self": 1.2280070222914219e-06 }, "TrainerController._save_models": { "total": 0.2750347309629433, "count": 1, "self": 0.002131151966750622, "children": { "RLTrainer._checkpoint": { "total": 0.27290357899619266, "count": 1, "self": 0.27290357899619266 } } } } } } }