{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.5059399604797363, "min": 1.4319477081298828, "max": 1.6117600202560425, "count": 301 }, "SoccerTwos.Policy.Entropy.sum": { "value": 30938.03125, "min": 1558.8505859375, "max": 35971.828125, "count": 301 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 69.6056338028169, "min": 23.0, "max": 79.74193548387096, "count": 301 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19768.0, "min": 368.0, "max": 21180.0, "count": 301 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1246.8471832362964, "min": 1189.6382320330763, "max": 1273.867379861165, "count": 301 }, "SoccerTwos.Self-play.ELO.sum": { "value": 177052.3000195541, "min": 9586.127309492153, "max": 282188.65309644124, "count": 301 }, "SoccerTwos.Step.mean": { "value": 19999990.0, "min": 16999970.0, "max": 19999990.0, "count": 301 }, "SoccerTwos.Step.sum": { "value": 19999990.0, "min": 16999970.0, "max": 19999990.0, "count": 301 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.032287657260894775, "min": -0.12829278409481049, "max": 0.0702536478638649, "count": 301 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -4.584847450256348, "min": -25.83823585510254, "max": 12.294387817382812, "count": 301 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.026449164375662804, "min": -0.12863744795322418, "max": 0.07054764032363892, "count": 301 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -3.755781412124634, "min": -25.118663787841797, "max": 12.345837593078613, "count": 301 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 301 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 301 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.09355493078769093, "min": -0.37945442337568114, "max": 0.3102267581812093, "count": 301 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -13.284800171852112, "min": -55.77980023622513, "max": 44.05219966173172, "count": 301 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.09355493078769093, "min": -0.37945442337568114, "max": 0.3102267581812093, "count": 301 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -13.284800171852112, "min": -55.77980023622513, "max": 44.05219966173172, "count": 301 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 301 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 301 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.018065121199470013, "min": 0.010378121212124825, "max": 0.02473225532254825, "count": 145 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.018065121199470013, "min": 0.010378121212124825, "max": 0.02473225532254825, "count": 145 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.09091534689068795, "min": 0.09007394015789032, "max": 0.11795357093214989, "count": 145 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.09091534689068795, "min": 0.09007394015789032, "max": 0.11795357093214989, "count": 145 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.09234057664871216, "min": 0.0911927747229735, "max": 0.12005007788538932, "count": 145 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.09234057664871216, "min": 0.0911927747229735, "max": 0.12005007788538932, "count": 145 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 145 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 145 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 145 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 145 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 145 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 145 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1690895478", "python_version": "3.9.13 (tags/v3.9.13:6de2ca5, May 17 2022, 16:36:42) [MSC v.1929 64 bit (AMD64)]", "command_line_arguments": "D:\\Python\\turtledove39\\Scripts\\mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.exe --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": "2.0.1+cpu", "numpy_version": "1.21.2", "end_time_seconds": "1690907636" }, "total": 12157.8615709, "count": 1, "self": 2.359178400001838, "children": { "run_training.setup": { "total": 0.2948898999999976, "count": 1, "self": 0.2948898999999976 }, "TrainerController.start_learning": { "total": 12155.207502599998, "count": 1, "self": 6.265188600000329, "children": { "TrainerController._reset_env": { "total": 8.819070700000559, "count": 16, "self": 8.819070700000559 }, "TrainerController.advance": { "total": 12139.947929799997, "count": 208372, "self": 5.875391699923057, "children": { "env_step": { "total": 4773.789322800094, "count": 208372, "self": 3758.485206099992, "children": { "SubprocessEnvManager._take_step": { "total": 1011.6621459001269, "count": 208372, "self": 35.81118820006054, "children": { "TorchPolicy.evaluate": { "total": 975.8509577000664, "count": 376390, "self": 975.8509577000664 } } }, "workers": { "total": 3.641970799974871, "count": 208372, "self": 0.0, "children": { "worker_root": { "total": 12140.297951199937, "count": 208372, "is_parallel": true, "self": 9065.13143900015, "children": { "steps_from_proto": { "total": 0.06633240000306184, "count": 32, "is_parallel": true, "self": 0.006828700005497623, "children": { "_process_rank_one_or_two_observation": { "total": 0.05950369999756422, "count": 128, "is_parallel": true, "self": 0.05950369999756422 } } }, "UnityEnvironment.step": { "total": 3075.1001797997847, "count": 208372, "is_parallel": true, "self": 156.08862579947663, "children": { "UnityEnvironment._generate_step_input": { "total": 119.95586170016085, "count": 208372, "is_parallel": true, "self": 119.95586170016085 }, "communicator.exchange": { "total": 2300.185689300237, "count": 208372, "is_parallel": true, "self": 2300.185689300237 }, "steps_from_proto": { "total": 498.8700029999106, "count": 416744, "is_parallel": true, "self": 98.83645789880103, "children": { "_process_rank_one_or_two_observation": { "total": 400.03354510110955, "count": 1666976, "is_parallel": true, "self": 400.03354510110955 } } } } } } } } } } }, "trainer_advance": { "total": 7360.283215299979, "count": 208372, "self": 42.508584399726715, "children": { "process_trajectory": { "total": 1131.9221432002605, "count": 208372, "self": 1128.0133847002621, "children": { "RLTrainer._checkpoint": { "total": 3.908758499998484, "count": 7, "self": 3.908758499998484 } } }, "_update_policy": { "total": 6185.852487699992, "count": 145, "self": 555.3977262999942, "children": { "TorchPOCAOptimizer.update": { "total": 5630.454761399998, "count": 4350, "self": 5630.454761399998 } } } } } } }, "trainer_threads": { "total": 8.999995770864189e-07, "count": 1, "self": 8.999995770864189e-07 }, "TrainerController._save_models": { "total": 0.1753126000003249, "count": 1, "self": 0.0032988000002660556, "children": { "RLTrainer._checkpoint": { "total": 0.17201380000005884, "count": 1, "self": 0.17201380000005884 } } } } } } }