{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 3.102017641067505, "min": 2.041501998901367, "max": 3.136293888092041, "count": 370 }, "SoccerTwos.Policy.Entropy.sum": { "value": 48341.84375, "min": 1437.2174072265625, "max": 140688.5625, "count": 370 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 882.4, "min": 361.8, "max": 999.0, "count": 370 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 17648.0, "min": 3996.0, "max": 31968.0, "count": 370 }, "SoccerTwos.Step.mean": { "value": 4999268.0, "min": 889928.0, "max": 4999268.0, "count": 412 }, "SoccerTwos.Step.sum": { "value": 4999268.0, "min": 889928.0, "max": 4999268.0, "count": 412 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.001689090859144926, "min": -0.01103414036333561, "max": 0.021417981013655663, "count": 412 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -0.0185799989849329, "min": -0.12137554585933685, "max": 0.21417981386184692, "count": 412 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.001865422003902495, "min": -0.008956444449722767, "max": 0.014903930947184563, "count": 412 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -0.020519642159342766, "min": -0.08956444263458252, "max": 0.14903931319713593, "count": 412 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 412 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 412 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": 0.1060727292841131, "min": -0.36363636363636365, "max": 0.1495636376467618, "count": 412 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 1.1668000221252441, "min": -4.702000021934509, "max": 2.2516000270843506, "count": 412 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.1060727292841131, "min": -0.36363636363636365, "max": 0.1495636376467618, "count": 412 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 1.1668000221252441, "min": -4.702000021934509, "max": 2.2516000270843506, "count": 412 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 412 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 412 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.020040803001029416, "min": 0.011714485075208359, "max": 0.02307238254612053, "count": 161 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.020040803001029416, "min": 0.011714485075208359, "max": 0.02307238254612053, "count": 161 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 7.547141746423828e-05, "min": 7.365118520002372e-09, "max": 0.004154800864246984, "count": 161 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 7.547141746423828e-05, "min": 7.365118520002372e-09, "max": 0.004154800864246984, "count": 161 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 7.55631832362269e-05, "min": 1.148362090851328e-08, "max": 0.004176822351291775, "count": 161 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 7.55631832362269e-05, "min": 1.148362090851328e-08, "max": 0.004176822351291775, "count": 161 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 161 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 161 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.19999999999999993, "max": 0.20000000000000007, "count": 161 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.19999999999999993, "max": 0.20000000000000007, "count": 161 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 161 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 161 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1202.9464461465905, "min": 1194.2669302859135, "max": 1202.9464461465905, "count": 77 }, "SoccerTwos.Self-play.ELO.sum": { "value": 2405.892892293181, "min": 2388.533860571827, "max": 11993.45423655682, "count": 77 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1682547728", "python_version": "3.9.16 (main, Mar 8 2023, 10:39:24) [MSC v.1916 64 bit (AMD64)]", "command_line_arguments": "C:\\Users\\Usuario\\miniconda3\\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": "2.0.0+cpu", "numpy_version": "1.21.2", "end_time_seconds": "1682556315" }, "total": 8587.9091326, "count": 1, "self": 0.1926858999995602, "children": { "run_training.setup": { "total": 0.07200840000000008, "count": 1, "self": 0.07200840000000008 }, "TrainerController.start_learning": { "total": 8587.6444383, "count": 1, "self": 3.1742184997965524, "children": { "TrainerController._reset_env": { "total": 3.429319399999788, "count": 22, "self": 3.429319399999788 }, "TrainerController.advance": { "total": 8580.943845500202, "count": 264991, "self": 3.1068143002830766, "children": { "env_step": { "total": 2837.7315885999305, "count": 264991, "self": 2184.696096199588, "children": { "SubprocessEnvManager._take_step": { "total": 650.9614059002138, "count": 264991, "self": 21.13272529962228, "children": { "TorchPolicy.evaluate": { "total": 629.8286806005915, "count": 527778, "self": 629.8286806005915 } } }, "workers": { "total": 2.0740865001289484, "count": 264991, "self": 0.0, "children": { "worker_root": { "total": 8580.296777699983, "count": 264991, "is_parallel": true, "self": 6847.639169299801, "children": { "steps_from_proto": { "total": 0.02831589999823514, "count": 44, "is_parallel": true, "self": 0.005754299997616119, "children": { "_process_rank_one_or_two_observation": { "total": 0.02256160000061902, "count": 176, "is_parallel": true, "self": 0.02256160000061902 } } }, "UnityEnvironment.step": { "total": 1732.6292925001835, "count": 264991, "is_parallel": true, "self": 92.05950100037671, "children": { "UnityEnvironment._generate_step_input": { "total": 80.91232160010361, "count": 264991, "is_parallel": true, "self": 80.91232160010361 }, "communicator.exchange": { "total": 1269.1824767999185, "count": 264991, "is_parallel": true, "self": 1269.1824767999185 }, "steps_from_proto": { "total": 290.47499309978446, "count": 529982, "is_parallel": true, "self": 55.97875599981586, "children": { "_process_rank_one_or_two_observation": { "total": 234.4962370999686, "count": 2119928, "is_parallel": true, "self": 234.4962370999686 } } } } } } } } } } }, "trainer_advance": { "total": 5740.105442599988, "count": 264991, "self": 33.02598739999121, "children": { "process_trajectory": { "total": 665.0356726999944, "count": 264991, "self": 664.1719426999931, "children": { "RLTrainer._checkpoint": { "total": 0.8637300000013113, "count": 9, "self": 0.8637300000013113 } } }, "_update_policy": { "total": 5042.043782500003, "count": 161, "self": 463.78144229999, "children": { "TorchPOCAOptimizer.update": { "total": 4578.262340200013, "count": 5748, "self": 4578.262340200013 } } } } } } }, "trainer_threads": { "total": 6.999998731771484e-07, "count": 1, "self": 6.999998731771484e-07 }, "TrainerController._save_models": { "total": 0.09705420000136655, "count": 1, "self": 0.006680700000288198, "children": { "RLTrainer._checkpoint": { "total": 0.09037350000107836, "count": 1, "self": 0.09037350000107836 } } } } } } }