{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.652201771736145, "min": 1.6454737186431885, "max": 3.295718193054199, "count": 1064 }, "SoccerTwos.Policy.Entropy.sum": { "value": 31775.14453125, "min": 11873.9892578125, "max": 125012.0625, "count": 1064 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 57.811764705882354, "min": 42.19827586206897, "max": 999.0, "count": 1064 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19656.0, "min": 9712.0, "max": 28624.0, "count": 1064 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1617.0756943274994, "min": 1187.911753721827, "max": 1647.4013844219048, "count": 998 }, "SoccerTwos.Self-play.ELO.sum": { "value": 274902.8680356749, "min": 2376.9959188058983, "max": 376134.1197163431, "count": 998 }, "SoccerTwos.Step.mean": { "value": 10639998.0, "min": 9540.0, "max": 10639998.0, "count": 1064 }, "SoccerTwos.Step.sum": { "value": 10639998.0, "min": 9540.0, "max": 10639998.0, "count": 1064 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.015043281018733978, "min": -0.12756769359111786, "max": 0.2135513424873352, "count": 1064 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -2.5423145294189453, "min": -22.38164520263672, "max": 27.06729507446289, "count": 1064 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.012198357842862606, "min": -0.12327215075492859, "max": 0.20781882107257843, "count": 1064 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -2.0615224838256836, "min": -23.006736755371094, "max": 26.394203186035156, "count": 1064 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 1064 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 1064 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": 0.06232189638374825, "min": -0.5494315812462255, "max": 0.6391851843139271, "count": 1064 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 10.532400488853455, "min": -51.174399852752686, "max": 63.113799929618835, "count": 1064 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.06232189638374825, "min": -0.5494315812462255, "max": 0.6391851843139271, "count": 1064 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 10.532400488853455, "min": -51.174399852752686, "max": 63.113799929618835, "count": 1064 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 1064 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 1064 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.017264949838863685, "min": 0.010595528713505093, "max": 0.02360185617969061, "count": 510 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.017264949838863685, "min": 0.010595528713505093, "max": 0.02360185617969061, "count": 510 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.10992388625939688, "min": 1.070836359910269e-06, "max": 0.12059773579239845, "count": 510 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.10992388625939688, "min": 1.070836359910269e-06, "max": 0.12059773579239845, "count": 510 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.11164524704217911, "min": 1.0474380530922645e-06, "max": 0.12335343509912491, "count": 510 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.11164524704217911, "min": 1.0474380530922645e-06, "max": 0.12335343509912491, "count": 510 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 510 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 510 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000004, "max": 0.20000000000000007, "count": 510 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000004, "max": 0.20000000000000007, "count": 510 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 510 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 510 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1677587703", "python_version": "3.9.16 | packaged by conda-forge | (main, Feb 1 2023, 21:28:38) [MSC v.1929 64 bit (AMD64)]", "command_line_arguments": "C:\\Users\\jonas\\.conda\\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+cu117", "numpy_version": "1.21.2", "end_time_seconds": "1677615712" }, "total": 28008.975405, "count": 1, "self": 0.06407110000145622, "children": { "run_training.setup": { "total": 0.13176489999999985, "count": 1, "self": 0.13176489999999985 }, "TrainerController.start_learning": { "total": 28008.779569, "count": 1, "self": 22.856993000114016, "children": { "TrainerController._reset_env": { "total": 7.18871370000327, "count": 54, "self": 7.18871370000327 }, "TrainerController.advance": { "total": 27978.46382059988, "count": 721773, "self": 21.633592700491135, "children": { "env_step": { "total": 19927.397306399507, "count": 721773, "self": 12892.338716699054, "children": { "SubprocessEnvManager._take_step": { "total": 7020.501626300867, "count": 721773, "self": 135.44392550302746, "children": { "TorchPolicy.evaluate": { "total": 6885.05770079784, "count": 1345596, "self": 6885.05770079784 } } }, "workers": { "total": 14.55696339958487, "count": 721772, "self": 0.0, "children": { "worker_root": { "total": 27972.65793990101, "count": 721772, "is_parallel": true, "self": 17872.508112801162, "children": { "steps_from_proto": { "total": 0.1578121999962363, "count": 108, "is_parallel": true, "self": 0.03201969997553755, "children": { "_process_rank_one_or_two_observation": { "total": 0.12579250002069875, "count": 432, "is_parallel": true, "self": 0.12579250002069875 } } }, "UnityEnvironment.step": { "total": 10099.992014899854, "count": 721772, "is_parallel": true, "self": 518.7492209000047, "children": { "UnityEnvironment._generate_step_input": { "total": 500.0139680008525, "count": 721772, "is_parallel": true, "self": 500.0139680008525 }, "communicator.exchange": { "total": 7328.479141999926, "count": 721772, "is_parallel": true, "self": 7328.479141999926 }, "steps_from_proto": { "total": 1752.7496839990706, "count": 1443544, "is_parallel": true, "self": 364.37890759439665, "children": { "_process_rank_one_or_two_observation": { "total": 1388.370776404674, "count": 5774176, "is_parallel": true, "self": 1388.370776404674 } } } } } } } } } } }, "trainer_advance": { "total": 8029.432921499883, "count": 721772, "self": 150.58379579841676, "children": { "process_trajectory": { "total": 3185.799990801456, "count": 721772, "self": 3180.7412104014497, "children": { "RLTrainer._checkpoint": { "total": 5.058780400006071, "count": 21, "self": 5.058780400006071 } } }, "_update_policy": { "total": 4693.049134900011, "count": 510, "self": 3000.620772200081, "children": { "TorchPOCAOptimizer.update": { "total": 1692.4283626999302, "count": 15306, "self": 1692.4283626999302 } } } } } } }, "trainer_threads": { "total": 1.3999997463542968e-06, "count": 1, "self": 1.3999997463542968e-06 }, "TrainerController._save_models": { "total": 0.27004029999807244, "count": 1, "self": 0.04116039999644272, "children": { "RLTrainer._checkpoint": { "total": 0.22887990000162972, "count": 1, "self": 0.22887990000162972 } } } } } } }