{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 3.162252187728882, "min": 3.162252187728882, "max": 3.2957398891448975, "count": 100 }, "SoccerTwos.Policy.Entropy.sum": { "value": 75995.2421875, "min": 25921.0078125, "max": 133110.59375, "count": 100 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 558.6, "min": 424.14285714285717, "max": 999.0, "count": 100 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 22344.0, "min": 11876.0, "max": 28368.0, "count": 100 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1214.3936844176385, "min": 1196.361178639922, "max": 1214.8056999139687, "count": 83 }, "SoccerTwos.Self-play.ELO.sum": { "value": 14572.724213011663, "min": 2392.722357279844, "max": 14572.724213011663, "count": 83 }, "SoccerTwos.Step.mean": { "value": 999800.0, "min": 9200.0, "max": 999800.0, "count": 100 }, "SoccerTwos.Step.sum": { "value": 999800.0, "min": 9200.0, "max": 999800.0, "count": 100 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.022672370076179504, "min": -0.06371298432350159, "max": 0.021307898685336113, "count": 100 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -0.4534474015235901, "min": -1.1468013525009155, "max": 0.3217635750770569, "count": 100 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.02146763913333416, "min": -0.06367100030183792, "max": 0.019453663378953934, "count": 100 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -0.4293527901172638, "min": -1.1460400819778442, "max": 0.3416339159011841, "count": 100 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 100 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 100 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.14093999862670897, "min": -0.47295999924341836, "max": 0.3928250018507242, "count": 100 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -2.8187999725341797, "min": -7.094399988651276, "max": 6.2852000296115875, "count": 100 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.14093999862670897, "min": -0.47295999924341836, "max": 0.3928250018507242, "count": 100 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -2.8187999725341797, "min": -7.094399988651276, "max": 6.2852000296115875, "count": 100 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 100 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 100 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.012548627756041241, "min": 0.01249065709222729, "max": 0.022648589235420027, "count": 46 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.012548627756041241, "min": 0.01249065709222729, "max": 0.022648589235420027, "count": 46 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.006773155058423678, "min": 1.445286061425577e-05, "max": 0.006773155058423678, "count": 46 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.006773155058423678, "min": 1.445286061425577e-05, "max": 0.006773155058423678, "count": 46 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.006792481305698554, "min": 1.4504865278771225e-05, "max": 0.006792481305698554, "count": 46 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.006792481305698554, "min": 1.4504865278771225e-05, "max": 0.006792481305698554, "count": 46 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 46 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 46 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 46 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 46 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 46 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 46 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1686133232", "python_version": "3.9.16 (main, Mar 8 2023, 10:39:24) [MSC v.1916 64 bit (AMD64)]", "command_line_arguments": "C:\\Users\\foong\\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": "2.0.1+cpu", "numpy_version": "1.21.2", "end_time_seconds": "1686137348" }, "total": 4116.6963604, "count": 1, "self": 0.42616520000046876, "children": { "run_training.setup": { "total": 0.1006718000000002, "count": 1, "self": 0.1006718000000002 }, "TrainerController.start_learning": { "total": 4116.1695234, "count": 1, "self": 2.2734087000380896, "children": { "TrainerController._reset_env": { "total": 3.4690902999998645, "count": 5, "self": 3.4690902999998645 }, "TrainerController.advance": { "total": 4110.225137399961, "count": 65163, "self": 2.5183218999527526, "children": { "env_step": { "total": 1819.2281803000146, "count": 65163, "self": 1420.6205691000682, "children": { "SubprocessEnvManager._take_step": { "total": 397.1312740999462, "count": 65163, "self": 13.21819270006688, "children": { "TorchPolicy.evaluate": { "total": 383.91308139987933, "count": 129386, "self": 383.91308139987933 } } }, "workers": { "total": 1.4763371000001149, "count": 65163, "self": 0.0, "children": { "worker_root": { "total": 4108.652217799923, "count": 65163, "is_parallel": true, "self": 2966.676160199945, "children": { "steps_from_proto": { "total": 0.014683500000186367, "count": 10, "is_parallel": true, "self": 0.0026850000003277863, "children": { "_process_rank_one_or_two_observation": { "total": 0.01199849999985858, "count": 40, "is_parallel": true, "self": 0.01199849999985858 } } }, "UnityEnvironment.step": { "total": 1141.9613740999775, "count": 65163, "is_parallel": true, "self": 64.81871039992097, "children": { "UnityEnvironment._generate_step_input": { "total": 52.98523710003018, "count": 65163, "is_parallel": true, "self": 52.98523710003018 }, "communicator.exchange": { "total": 812.326884199954, "count": 65163, "is_parallel": true, "self": 812.326884199954 }, "steps_from_proto": { "total": 211.83054240007243, "count": 130326, "is_parallel": true, "self": 40.816247799867625, "children": { "_process_rank_one_or_two_observation": { "total": 171.0142946002048, "count": 521304, "is_parallel": true, "self": 171.0142946002048 } } } } } } } } } } }, "trainer_advance": { "total": 2288.4786351999933, "count": 65163, "self": 16.39999309998484, "children": { "process_trajectory": { "total": 320.41879030000734, "count": 65163, "self": 319.8852327000071, "children": { "RLTrainer._checkpoint": { "total": 0.533557600000222, "count": 2, "self": 0.533557600000222 } } }, "_update_policy": { "total": 1951.6598518000012, "count": 46, "self": 203.0268397999971, "children": { "TorchPOCAOptimizer.update": { "total": 1748.633012000004, "count": 1380, "self": 1748.633012000004 } } } } } } }, "trainer_threads": { "total": 1.4000006558489986e-06, "count": 1, "self": 1.4000006558489986e-06 }, "TrainerController._save_models": { "total": 0.20188560000042344, "count": 1, "self": 0.005417700000180048, "children": { "RLTrainer._checkpoint": { "total": 0.1964679000002434, "count": 1, "self": 0.1964679000002434 } } } } } } }