{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 3.221144199371338, "min": 3.188920736312866, "max": 3.2957088947296143, "count": 50 }, "SoccerTwos.Policy.Entropy.sum": { "value": 86893.5859375, "min": 42178.09765625, "max": 105462.515625, "count": 50 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 928.1666666666666, "min": 485.1111111111111, "max": 999.0, "count": 50 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 22276.0, "min": 14168.0, "max": 28044.0, "count": 50 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1189.182282031378, "min": 1188.4081430847966, "max": 1202.4685887719338, "count": 38 }, "SoccerTwos.Self-play.ELO.sum": { "value": 2378.364564062756, "min": 2376.8162861695932, "max": 14389.387209866527, "count": 38 }, "SoccerTwos.Step.mean": { "value": 499812.0, "min": 9038.0, "max": 499812.0, "count": 50 }, "SoccerTwos.Step.sum": { "value": 499812.0, "min": 9038.0, "max": 499812.0, "count": 50 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.01624487154185772, "min": -0.029827257618308067, "max": -0.001312743523158133, "count": 50 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -0.17869359254837036, "min": -0.5384518504142761, "max": -0.022316640242934227, "count": 50 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.016229845583438873, "min": -0.03340421989560127, "max": -0.002580253640189767, "count": 50 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -0.1785283088684082, "min": -0.6346802115440369, "max": -0.03354329615831375, "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": 0.07716363668441772, "min": -0.625, "max": 0.23827693095574012, "count": 50 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 0.848800003528595, "min": -10.0, "max": 3.0976001024246216, "count": 50 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.07716363668441772, "min": -0.625, "max": 0.23827693095574012, "count": 50 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 0.848800003528595, "min": -10.0, "max": 3.0976001024246216, "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": 0.014975171471208644, "min": 0.011634940153938563, "max": 0.022144934178019562, "count": 23 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.014975171471208644, "min": 0.011634940153938563, "max": 0.022144934178019562, "count": 23 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.000778963102978499, "min": 4.6427225546115856e-05, "max": 0.006489968532696367, "count": 23 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.000778963102978499, "min": 4.6427225546115856e-05, "max": 0.006489968532696367, "count": 23 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.0007812570198439062, "min": 4.9472472892375666e-05, "max": 0.006601646480460962, "count": 23 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.0007812570198439062, "min": 4.9472472892375666e-05, "max": 0.006601646480460962, "count": 23 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 23 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 23 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 23 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 23 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 23 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 23 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1703691093", "python_version": "3.10.12 | packaged by Anaconda, Inc. | (main, Jul 5 2023, 19:01:18) [MSC v.1916 64 bit (AMD64)]", "command_line_arguments": "\\\\?\\C:\\Users\\Sam\\anaconda3\\envs\\hf-rl\\Scripts\\mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.exe --run-id=SoccerTwos2 --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.1.2+cpu", "numpy_version": "1.23.5", "end_time_seconds": "1703692120" }, "total": 1027.0313427, "count": 1, "self": 0.47245939999993425, "children": { "run_training.setup": { "total": 0.10348060000069381, "count": 1, "self": 0.10348060000069381 }, "TrainerController.start_learning": { "total": 1026.4554026999995, "count": 1, "self": 0.3790510998478567, "children": { "TrainerController._reset_env": { "total": 3.148382799998217, "count": 3, "self": 3.148382799998217 }, "TrainerController.advance": { "total": 1022.8390034001532, "count": 32953, "self": 0.3991325004353712, "children": { "env_step": { "total": 361.635755599631, "count": 32953, "self": 272.21735489981074, "children": { "SubprocessEnvManager._take_step": { "total": 89.17183589986598, "count": 32953, "self": 2.8537339002523368, "children": { "TorchPolicy.evaluate": { "total": 86.31810199961365, "count": 65432, "self": 86.31810199961365 } } }, "workers": { "total": 0.24656479995428526, "count": 32953, "self": 0.0, "children": { "worker_root": { "total": 1022.7023911000233, "count": 32953, "is_parallel": true, "self": 808.1815209998422, "children": { "steps_from_proto": { "total": 0.003891899998052395, "count": 6, "is_parallel": true, "self": 0.0007979999954841333, "children": { "_process_rank_one_or_two_observation": { "total": 0.0030939000025682617, "count": 24, "is_parallel": true, "self": 0.0030939000025682617 } } }, "UnityEnvironment.step": { "total": 214.51697820018308, "count": 32953, "is_parallel": true, "self": 12.72579990014674, "children": { "UnityEnvironment._generate_step_input": { "total": 11.795844799828046, "count": 32953, "is_parallel": true, "self": 11.795844799828046 }, "communicator.exchange": { "total": 151.39225170007558, "count": 32953, "is_parallel": true, "self": 151.39225170007558 }, "steps_from_proto": { "total": 38.60308180013271, "count": 65906, "is_parallel": true, "self": 7.4401286005831935, "children": { "_process_rank_one_or_two_observation": { "total": 31.16295319954952, "count": 263624, "is_parallel": true, "self": 31.16295319954952 } } } } } } } } } } }, "trainer_advance": { "total": 660.8041153000868, "count": 32953, "self": 3.57287010010441, "children": { "process_trajectory": { "total": 82.72817269997904, "count": 32953, "self": 82.6200198999777, "children": { "RLTrainer._checkpoint": { "total": 0.10815280000133498, "count": 1, "self": 0.10815280000133498 } } }, "_update_policy": { "total": 574.5030725000033, "count": 23, "self": 56.93176390002736, "children": { "TorchPOCAOptimizer.update": { "total": 517.571308599976, "count": 690, "self": 517.571308599976 } } } } } } }, "trainer_threads": { "total": 1.3999997463542968e-06, "count": 1, "self": 1.3999997463542968e-06 }, "TrainerController._save_models": { "total": 0.08896400000048743, "count": 1, "self": 0.006688400000712136, "children": { "RLTrainer._checkpoint": { "total": 0.0822755999997753, "count": 1, "self": 0.0822755999997753 } } } } } } }