{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 3.1837267875671387, "min": 3.174865961074829, "max": 3.295696258544922, "count": 50 }, "SoccerTwos.Policy.Entropy.sum": { "value": 82624.078125, "min": 30336.0703125, "max": 123845.171875, "count": 50 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 247.10526315789474, "min": 241.26315789473685, "max": 999.0, "count": 50 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 18780.0, "min": 3996.0, "max": 32732.0, "count": 50 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1221.9633330317247, "min": 1197.722151511462, "max": 1221.9633330317247, "count": 46 }, "SoccerTwos.Self-play.ELO.sum": { "value": 41546.75332307864, "min": 2395.4649066522998, "max": 41546.75332307864, "count": 46 }, "SoccerTwos.Step.mean": { "value": 499870.0, "min": 9716.0, "max": 499870.0, "count": 50 }, "SoccerTwos.Step.sum": { "value": 499870.0, "min": 9716.0, "max": 499870.0, "count": 50 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": 0.01619746908545494, "min": -0.07889527827501297, "max": 0.03625180199742317, "count": 50 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": 0.6155038475990295, "min": -1.0400186777114868, "max": 0.8341204524040222, "count": 50 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": 0.01718762144446373, "min": -0.07891540229320526, "max": 0.03306958079338074, "count": 50 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": 0.6531296372413635, "min": -1.1213264465332031, "max": 0.913951575756073, "count": 50 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 50 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 50 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": 0.23280000059228195, "min": -0.4609846153941292, "max": 0.3775000050663948, "count": 50 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 8.846400022506714, "min": -11.317799985408783, "max": 8.846400022506714, "count": 50 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.23280000059228195, "min": -0.4609846153941292, "max": 0.3775000050663948, "count": 50 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 8.846400022506714, "min": -11.317799985408783, "max": 8.846400022506714, "count": 50 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 50 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 50 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.01674096918577561, "min": 0.01076800278679002, "max": 0.020453594511491247, "count": 22 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.01674096918577561, "min": 0.01076800278679002, "max": 0.020453594511491247, "count": 22 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.012350888270884753, "min": 0.00186826151330024, "max": 0.012350888270884753, "count": 22 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.012350888270884753, "min": 0.00186826151330024, "max": 0.012350888270884753, "count": 22 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.012647064154346783, "min": 0.001882767454177762, "max": 0.012647064154346783, "count": 22 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.012647064154346783, "min": 0.001882767454177762, "max": 0.012647064154346783, "count": 22 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 22 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 22 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.19999999999999996, "max": 0.20000000000000007, "count": 22 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.19999999999999996, "max": 0.20000000000000007, "count": 22 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 22 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 22 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1691879255", "python_version": "3.9.17 (main, Jul 5 2023, 20:47:11) [MSC v.1916 64 bit (AMD64)]", "command_line_arguments": "\\\\?\\C:\\Users\\Lenovo T15\\miniconda3\\envs\\rl\\Scripts\\mlagents-learn C:\\Users\\Lenovo T15\\Desktop\\ml-agents-develop\\config\\poca\\SoccerTwos.yaml --env=C:\\Users\\Lenovo T15\\Desktop\\ml-agents-develop\\ml-agents\\training-envs-executables\\SoccerTwos\\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": "2.0.1+cpu", "numpy_version": "1.21.2", "end_time_seconds": "1691881545" }, "total": 2289.8978065, "count": 1, "self": 1.2829630000001089, "children": { "run_training.setup": { "total": 0.13826530000000004, "count": 1, "self": 0.13826530000000004 }, "TrainerController.start_learning": { "total": 2288.4765782, "count": 1, "self": 1.2757949999727316, "children": { "TrainerController._reset_env": { "total": 7.81631329999993, "count": 3, "self": 7.81631329999993 }, "TrainerController.advance": { "total": 2279.030182400027, "count": 33049, "self": 1.3813639999852967, "children": { "env_step": { "total": 949.3254267000216, "count": 33049, "self": 726.9567290000521, "children": { "SubprocessEnvManager._take_step": { "total": 221.54427709998154, "count": 33049, "self": 7.533042099978758, "children": { "TorchPolicy.evaluate": { "total": 214.01123500000278, "count": 65512, "self": 214.01123500000278 } } }, "workers": { "total": 0.8244205999879455, "count": 33049, "self": 0.0, "children": { "worker_root": { "total": 2278.3523212999908, "count": 33049, "is_parallel": true, "self": 1703.6007957999964, "children": { "steps_from_proto": { "total": 0.006782200000002625, "count": 6, "is_parallel": true, "self": 0.0013350999999603985, "children": { "_process_rank_one_or_two_observation": { "total": 0.0054471000000422265, "count": 24, "is_parallel": true, "self": 0.0054471000000422265 } } }, "UnityEnvironment.step": { "total": 574.7447432999945, "count": 33049, "is_parallel": true, "self": 31.949409099980926, "children": { "UnityEnvironment._generate_step_input": { "total": 24.0562025000033, "count": 33049, "is_parallel": true, "self": 24.0562025000033 }, "communicator.exchange": { "total": 413.36170250000623, "count": 33049, "is_parallel": true, "self": 413.36170250000623 }, "steps_from_proto": { "total": 105.3774292000041, "count": 66098, "is_parallel": true, "self": 19.980756000052068, "children": { "_process_rank_one_or_two_observation": { "total": 85.39667319995203, "count": 264392, "is_parallel": true, "self": 85.39667319995203 } } } } } } } } } } }, "trainer_advance": { "total": 1328.3233917000202, "count": 33049, "self": 8.35604420003665, "children": { "process_trajectory": { "total": 182.78447379998295, "count": 33049, "self": 182.32841529998302, "children": { "RLTrainer._checkpoint": { "total": 0.4560584999999264, "count": 1, "self": 0.4560584999999264 } } }, "_update_policy": { "total": 1137.1828737000005, "count": 22, "self": 109.53007320000052, "children": { "TorchPOCAOptimizer.update": { "total": 1027.6528005, "count": 675, "self": 1027.6528005 } } } } } } }, "TrainerController._save_models": { "total": 0.3542875000002823, "count": 1, "self": 3.040000001419685e-05, "children": { "RLTrainer._checkpoint": { "total": 0.3542571000002681, "count": 1, "self": 0.3542571000002681 } } } } } } }