{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.5866121053695679, "min": 1.527618646621704, "max": 3.2174642086029053, "count": 961 }, "SoccerTwos.Policy.Entropy.sum": { "value": 32493.81640625, "min": 6953.41748046875, "max": 159545.171875, "count": 961 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 50.12244897959184, "min": 40.21666666666667, "max": 999.0, "count": 961 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19648.0, "min": 1252.0, "max": 31432.0, "count": 961 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1462.7843713394097, "min": 1195.6239676801113, "max": 1534.4058743689864, "count": 926 }, "SoccerTwos.Self-play.ELO.sum": { "value": 286705.7367825243, "min": 2391.2479353602225, "max": 357247.09576504957, "count": 926 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 961 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 961 }, "SoccerTwos.Step.mean": { "value": 10099984.0, "min": 509840.0, "max": 10099984.0, "count": 960 }, "SoccerTwos.Step.sum": { "value": 10099984.0, "min": 509840.0, "max": 10099984.0, "count": 960 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.06891822814941406, "min": -0.14169293642044067, "max": 0.16339489817619324, "count": 960 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -13.507972717285156, "min": -26.63827133178711, "max": 25.03961181640625, "count": 960 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.0703696683049202, "min": -0.13789178431034088, "max": 0.167164608836174, "count": 960 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -13.792455673217773, "min": -25.923654556274414, "max": 25.369762420654297, "count": 960 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 960 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 960 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.0867428572810426, "min": -0.5304761919237319, "max": 0.4851259258058336, "count": 960 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -17.00160002708435, "min": -54.925999879837036, "max": 56.5091997385025, "count": 960 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.0867428572810426, "min": -0.5304761919237319, "max": 0.4851259258058336, "count": 960 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -17.00160002708435, "min": -54.925999879837036, "max": 56.5091997385025, "count": 960 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.01604358012555167, "min": 0.009785405876270185, "max": 0.02438918145150334, "count": 461 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.01604358012555167, "min": 0.009785405876270185, "max": 0.02438918145150334, "count": 461 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.12075758377710978, "min": 8.424399216740616e-07, "max": 0.12673227315147717, "count": 461 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.12075758377710978, "min": 8.424399216740616e-07, "max": 0.12673227315147717, "count": 461 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.12336124951640765, "min": 8.604714347863288e-07, "max": 0.12984081829587618, "count": 461 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.12336124951640765, "min": 8.604714347863288e-07, "max": 0.12984081829587618, "count": 461 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 461 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 461 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.19999999999999996, "max": 0.20000000000000007, "count": 461 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.19999999999999996, "max": 0.20000000000000007, "count": 461 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 461 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 461 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1684243551", "python_version": "3.9.16 (main, Mar 8 2023, 10:39:24) [MSC v.1916 64 bit (AMD64)]", "command_line_arguments": "C:\\ProgramData\\anaconda3\\envs\\rl\\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": "1684307269" }, "total": 63718.5219284, "count": 1, "self": 2.7861281000004965, "children": { "run_training.setup": { "total": 0.21971890000000016, "count": 1, "self": 0.21971890000000016 }, "TrainerController.start_learning": { "total": 63715.5160814, "count": 1, "self": 25.563273298765125, "children": { "TrainerController._reset_env": { "total": 23.362592199984995, "count": 97, "self": 23.362592199984995 }, "TrainerController.advance": { "total": 63666.30404140124, "count": 665938, "self": 23.20057059924875, "children": { "env_step": { "total": 19977.192617300956, "count": 665938, "self": 15309.20797199773, "children": { "SubprocessEnvManager._take_step": { "total": 4650.740881002019, "count": 665938, "self": 165.74838670110694, "children": { "TorchPolicy.evaluate": { "total": 4484.992494300912, "count": 1222556, "self": 4484.992494300912 } } }, "workers": { "total": 17.243764301206767, "count": 665938, "self": 0.0, "children": { "worker_root": { "total": 63602.547887296896, "count": 665938, "is_parallel": true, "self": 51273.08974479824, "children": { "steps_from_proto": { "total": 0.35863439998501434, "count": 194, "is_parallel": true, "self": 0.0657623999876975, "children": { "_process_rank_one_or_two_observation": { "total": 0.29287199999731683, "count": 776, "is_parallel": true, "self": 0.29287199999731683 } } }, "UnityEnvironment.step": { "total": 12329.099508098669, "count": 665938, "is_parallel": true, "self": 752.6750525024345, "children": { "UnityEnvironment._generate_step_input": { "total": 677.5573044998821, "count": 665938, "is_parallel": true, "self": 677.5573044998821 }, "communicator.exchange": { "total": 8538.213244295146, "count": 665938, "is_parallel": true, "self": 8538.213244295146 }, "steps_from_proto": { "total": 2360.6539068012066, "count": 1331876, "is_parallel": true, "self": 438.56148160226144, "children": { "_process_rank_one_or_two_observation": { "total": 1922.0924251989452, "count": 5327504, "is_parallel": true, "self": 1922.0924251989452 } } } } } } } } } } }, "trainer_advance": { "total": 43665.91085350104, "count": 665938, "self": 169.67386100112344, "children": { "process_trajectory": { "total": 6299.385353299973, "count": 665938, "self": 6294.3278008999905, "children": { "RLTrainer._checkpoint": { "total": 5.057552399982548, "count": 20, "self": 5.057552399982548 } } }, "_update_policy": { "total": 37196.851639199944, "count": 462, "self": 2144.8734003001955, "children": { "TorchPOCAOptimizer.update": { "total": 35051.97823889975, "count": 13867, "self": 35051.97823889975 } } } } } } }, "trainer_threads": { "total": 3.0000010156072676e-06, "count": 1, "self": 3.0000010156072676e-06 }, "TrainerController._save_models": { "total": 0.2861715000035474, "count": 1, "self": 0.01669680000486551, "children": { "RLTrainer._checkpoint": { "total": 0.2694746999986819, "count": 1, "self": 0.2694746999986819 } } } } } } }