{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.0846117734909058, "min": 1.0645475387573242, "max": 1.92023766040802, "count": 2548 }, "SoccerTwos.Policy.Entropy.sum": { "value": 23497.029296875, "min": 18337.876953125, "max": 47723.1640625, "count": 2548 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 75.2089552238806, "min": 54.68888888888889, "max": 214.08333333333334, "count": 2548 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 20156.0, "min": 6272.0, "max": 22288.0, "count": 2548 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1699.1947668306916, "min": 1369.873781563621, "max": 1699.1947668306916, "count": 2548 }, "SoccerTwos.Self-play.ELO.sum": { "value": 227692.09875531268, "min": 44258.13077522131, "max": 302028.7027379467, "count": 2548 }, "SoccerTwos.Step.mean": { "value": 31599876.0, "min": 6129964.0, "max": 31599876.0, "count": 2548 }, "SoccerTwos.Step.sum": { "value": 31599876.0, "min": 6129964.0, "max": 31599876.0, "count": 2548 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": 0.0069866664707660675, "min": -0.13620364665985107, "max": 0.13637112081050873, "count": 2548 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": 0.9292266368865967, "min": -17.861400604248047, "max": 13.500741004943848, "count": 2548 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": 0.010481107048690319, "min": -0.13413482904434204, "max": 0.13434651494026184, "count": 2548 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": 1.3939871788024902, "min": -18.2657527923584, "max": 13.300305366516113, "count": 2548 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 2548 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 2548 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.033372930566171057, "min": -0.5607882334905512, "max": 0.5252131184593576, "count": 2548 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -4.438599765300751, "min": -53.153600215911865, "max": 45.61839985847473, "count": 2548 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.033372930566171057, "min": -0.5607882334905512, "max": 0.5252131184593576, "count": 2548 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -4.438599765300751, "min": -53.153600215911865, "max": 45.61839985847473, "count": 2548 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 2548 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 2548 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.02525031388795469, "min": 0.020803033336414957, "max": 0.041260043921647595, "count": 1233 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.02525031388795469, "min": 0.020803033336414957, "max": 0.041260043921647595, "count": 1233 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.07839210368692875, "min": 0.033978474559262395, "max": 0.08665177673101425, "count": 1233 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.07839210368692875, "min": 0.033978474559262395, "max": 0.08665177673101425, "count": 1233 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.0796885147690773, "min": 0.03553536711260676, "max": 0.08805550690740346, "count": 1233 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.0796885147690773, "min": 0.03553536711260676, "max": 0.08805550690740346, "count": 1233 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.000368156503184356, "min": 0.000368156503184356, "max": 0.0008770491322950879, "count": 1233 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.000368156503184356, "min": 0.000368156503184356, "max": 0.0008770491322950879, "count": 1233 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.13681564400000001, "min": 0.13681564400000001, "max": 0.187704912, "count": 1233 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.13681564400000001, "min": 0.13681564400000001, "max": 0.187704912, "count": 1233 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.0018471006356, "min": 0.0018471006356, "max": 0.0043864751088, "count": 1233 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.0018471006356, "min": 0.0018471006356, "max": 0.0043864751088, "count": 1233 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1686645220", "python_version": "3.9.16 (main, Mar 8 2023, 14:00:05) \n[GCC 11.2.0]", "command_line_arguments": "/home/vic/miniconda3/envs/rl/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.x86_64 --run-id=SoccerTwos --no-graphics --resume", "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": "1686668633" }, "total": 23413.273160344997, "count": 1, "self": 0.08570258099643979, "children": { "run_training.setup": { "total": 0.0066065460000572784, "count": 1, "self": 0.0066065460000572784 }, "TrainerController.start_learning": { "total": 23413.180851218, "count": 1, "self": 23.49731805194824, "children": { "TrainerController._reset_env": { "total": 3.139995149985225, "count": 129, "self": 3.139995149985225 }, "TrainerController.advance": { "total": 23386.411966905067, "count": 1710413, "self": 24.415025666803558, "children": { "env_step": { "total": 17161.444373879633, "count": 1710413, "self": 13347.780332518845, "children": { "SubprocessEnvManager._take_step": { "total": 3800.495580301883, "count": 1710413, "self": 137.7720913263397, "children": { "TorchPolicy.evaluate": { "total": 3662.723488975543, "count": 3204825, "self": 3662.723488975543 } } }, "workers": { "total": 13.168461058904995, "count": 1710412, "self": 0.0, "children": { "worker_root": { "total": 23377.722085329642, "count": 1710412, "is_parallel": true, "self": 12431.808752011784, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0016754660000515287, "count": 2, "is_parallel": true, "self": 0.0005117519995110342, "children": { "_process_rank_one_or_two_observation": { "total": 0.0011637140005404945, "count": 8, "is_parallel": true, "self": 0.0011637140005404945 } } }, "UnityEnvironment.step": { "total": 0.019840541000121448, "count": 1, "is_parallel": true, "self": 0.00038042400001359056, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00025097899970205617, "count": 1, "is_parallel": true, "self": 0.00025097899970205617 }, "communicator.exchange": { "total": 0.018085425000208488, "count": 1, "is_parallel": true, "self": 0.018085425000208488 }, "steps_from_proto": { "total": 0.0011237130001973128, "count": 2, "is_parallel": true, "self": 0.00020778399903065292, "children": { "_process_rank_one_or_two_observation": { "total": 0.0009159290011666599, "count": 8, "is_parallel": true, "self": 0.0009159290011666599 } } } } } } }, "steps_from_proto": { "total": 0.14613365500326836, "count": 256, "is_parallel": true, "self": 0.02698711999119041, "children": { "_process_rank_one_or_two_observation": { "total": 0.11914653501207795, "count": 1024, "is_parallel": true, "self": 0.11914653501207795 } } }, "UnityEnvironment.step": { "total": 10945.767199662854, "count": 1710411, "is_parallel": true, "self": 580.3152422990079, "children": { "UnityEnvironment._generate_step_input": { "total": 320.84550723172833, "count": 1710411, "is_parallel": true, "self": 320.84550723172833 }, "communicator.exchange": { "total": 8376.638963032485, "count": 1710411, "is_parallel": true, "self": 8376.638963032485 }, "steps_from_proto": { "total": 1667.9674870996332, "count": 3420822, "is_parallel": true, "self": 300.48039734707345, "children": { "_process_rank_one_or_two_observation": { "total": 1367.4870897525598, "count": 13683288, "is_parallel": true, "self": 1367.4870897525598 } } } } } } } } } } }, "trainer_advance": { "total": 6200.552567358629, "count": 1710412, "self": 154.9150582690745, "children": { "process_trajectory": { "total": 1921.0863046295212, "count": 1710412, "self": 1913.9652171165171, "children": { "RLTrainer._checkpoint": { "total": 7.121087513004113, "count": 51, "self": 7.121087513004113 } } }, "_update_policy": { "total": 4124.551204460033, "count": 1233, "self": 2825.05031355988, "children": { "TorchPOCAOptimizer.update": { "total": 1299.5008909001526, "count": 49320, "self": 1299.5008909001526 } } } } } } }, "trainer_threads": { "total": 7.460002962034196e-07, "count": 1, "self": 7.460002962034196e-07 }, "TrainerController._save_models": { "total": 0.13157036499978858, "count": 1, "self": 0.0014913829982106108, "children": { "RLTrainer._checkpoint": { "total": 0.13007898200157797, "count": 1, "self": 0.13007898200157797 } } } } } } }