{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 3.1724157333374023, "min": 3.159562349319458, "max": 3.295759677886963, "count": 132 }, "SoccerTwos.Policy.Entropy.sum": { "value": 53804.171875, "min": 21530.556640625, "max": 125230.8125, "count": 132 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 959.2, "min": 467.27272727272725, "max": 999.0, "count": 132 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19184.0, "min": 14332.0, "max": 26928.0, "count": 132 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1191.6003715591316, "min": 1191.6003715591316, "max": 1201.3562969440595, "count": 105 }, "SoccerTwos.Self-play.ELO.sum": { "value": 2383.2007431182633, "min": 2383.2007431182633, "max": 14337.393003833378, "count": 105 }, "SoccerTwos.Step.mean": { "value": 1319252.0, "min": 9482.0, "max": 1319252.0, "count": 132 }, "SoccerTwos.Step.sum": { "value": 1319252.0, "min": 9482.0, "max": 1319252.0, "count": 132 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.003095856634899974, "min": -0.018469562754034996, "max": 0.06517812609672546, "count": 132 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -0.030958566814661026, "min": -0.23690620064735413, "max": 0.9124724864959717, "count": 132 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.0034298759419471025, "min": -0.018163833767175674, "max": 0.0651244968175888, "count": 132 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -0.03429875895380974, "min": -0.21748584508895874, "max": 0.9115992784500122, "count": 132 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 132 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 132 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.2, "min": -0.5, "max": 0.27900000129427227, "count": 132 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -2.0, "min": -7.283200025558472, "max": 3.906000018119812, "count": 132 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.2, "min": -0.5, "max": 0.27900000129427227, "count": 132 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -2.0, "min": -7.283200025558472, "max": 3.906000018119812, "count": 132 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 132 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 132 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.017150057954131624, "min": 0.012152449223989, "max": 0.022745259787188842, "count": 61 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.017150057954131624, "min": 0.012152449223989, "max": 0.022745259787188842, "count": 61 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 5.299444007202207e-05, "min": 1.945017152138462e-06, "max": 0.0057295642948398985, "count": 61 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 5.299444007202207e-05, "min": 1.945017152138462e-06, "max": 0.0057295642948398985, "count": 61 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 4.586771301546832e-05, "min": 1.9585297460859388e-06, "max": 0.005752097365135948, "count": 61 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 4.586771301546832e-05, "min": 1.9585297460859388e-06, "max": 0.005752097365135948, "count": 61 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 61 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 61 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 61 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 61 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 61 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 61 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1676802310", "python_version": "3.9.16 (main, Jan 11 2023, 16:16:36) [MSC v.1916 64 bit (AMD64)]", "command_line_arguments": "C:\\Users\\maxim\\anaconda3\\envs\\rl\\Scripts\\mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.exe --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": "1.13.1+cpu", "numpy_version": "1.21.2", "end_time_seconds": "1676806384" }, "total": 4074.3048648, "count": 1, "self": 0.10456339999973352, "children": { "run_training.setup": { "total": 0.1486251000000003, "count": 1, "self": 0.1486251000000003 }, "TrainerController.start_learning": { "total": 4074.0516763, "count": 1, "self": 2.3457451999970544, "children": { "TrainerController._reset_env": { "total": 5.403853300000183, "count": 7, "self": 5.403853300000183 }, "TrainerController.advance": { "total": 4066.1464245000025, "count": 86330, "self": 2.425649199969939, "children": { "env_step": { "total": 1861.7718038000116, "count": 86330, "self": 1455.2553344999978, "children": { "SubprocessEnvManager._take_step": { "total": 404.9907094000079, "count": 86330, "self": 13.383302800044703, "children": { "TorchPolicy.evaluate": { "total": 391.6074065999632, "count": 171464, "self": 391.6074065999632 } } }, "workers": { "total": 1.5257599000059896, "count": 86330, "self": 0.0, "children": { "worker_root": { "total": 4062.8824515999936, "count": 86330, "is_parallel": true, "self": 2892.232263300039, "children": { "steps_from_proto": { "total": 0.016412799999756977, "count": 14, "is_parallel": true, "self": 0.0037419999996792797, "children": { "_process_rank_one_or_two_observation": { "total": 0.012670800000077698, "count": 56, "is_parallel": true, "self": 0.012670800000077698 } } }, "UnityEnvironment.step": { "total": 1170.633775499955, "count": 86330, "is_parallel": true, "self": 54.33172750005929, "children": { "UnityEnvironment._generate_step_input": { "total": 44.20012970002892, "count": 86330, "is_parallel": true, "self": 44.20012970002892 }, "communicator.exchange": { "total": 899.3830379999583, "count": 86330, "is_parallel": true, "self": 899.3830379999583 }, "steps_from_proto": { "total": 172.7188802999084, "count": 172660, "is_parallel": true, "self": 37.32282030008622, "children": { "_process_rank_one_or_two_observation": { "total": 135.39605999982217, "count": 690640, "is_parallel": true, "self": 135.39605999982217 } } } } } } } } } } }, "trainer_advance": { "total": 2201.948971500021, "count": 86330, "self": 15.604438399938317, "children": { "process_trajectory": { "total": 300.6176660000828, "count": 86330, "self": 300.25259540008295, "children": { "RLTrainer._checkpoint": { "total": 0.3650705999998536, "count": 2, "self": 0.3650705999998536 } } }, "_update_policy": { "total": 1885.7268670999997, "count": 62, "self": 225.91226669999924, "children": { "TorchPOCAOptimizer.update": { "total": 1659.8146004000005, "count": 1832, "self": 1659.8146004000005 } } } } } } }, "trainer_threads": { "total": 1.2000000424450263e-06, "count": 1, "self": 1.2000000424450263e-06 }, "TrainerController._save_models": { "total": 0.1556521000002249, "count": 1, "self": 0.010813600000346923, "children": { "RLTrainer._checkpoint": { "total": 0.14483849999987797, "count": 1, "self": 0.14483849999987797 } } } } } } }