{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.786329746246338, "min": 1.7352153062820435, "max": 2.136521816253662, "count": 448 }, "SoccerTwos.Policy.Entropy.sum": { "value": 34183.20703125, "min": 30564.755859375, "max": 45906.1796875, "count": 448 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 50.8041237113402, "min": 43.176991150442475, "max": 82.74193548387096, "count": 448 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19712.0, "min": 16128.0, "max": 20984.0, "count": 448 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1646.6143736491674, "min": 1542.4934933199522, "max": 1674.2226076085644, "count": 448 }, "SoccerTwos.Self-play.ELO.sum": { "value": 319443.1884879385, "min": 193472.31510238713, "max": 366434.1727897799, "count": 448 }, "SoccerTwos.Step.mean": { "value": 10439996.0, "min": 5969956.0, "max": 10439996.0, "count": 448 }, "SoccerTwos.Step.sum": { "value": 10439996.0, "min": 5969956.0, "max": 10439996.0, "count": 448 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.0018759375670924783, "min": -0.1282617747783661, "max": 0.09107836335897446, "count": 448 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -0.36393189430236816, "min": -19.23926544189453, "max": 17.66920280456543, "count": 448 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.003097682958468795, "min": -0.12756170332431793, "max": 0.09180551022291183, "count": 448 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -0.6009504795074463, "min": -19.134254455566406, "max": 17.81026840209961, "count": 448 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 448 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 448 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.07530309244529489, "min": -0.2813466668128967, "max": 0.24626746845532613, "count": 448 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -14.608799934387207, "min": -47.185999274253845, "max": 53.19280010461807, "count": 448 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.07530309244529489, "min": -0.2813466668128967, "max": 0.24626746845532613, "count": 448 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -14.608799934387207, "min": -47.185999274253845, "max": 53.19280010461807, "count": 448 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 448 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 448 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.01499969494373848, "min": 0.010806223685358418, "max": 0.024950472956212857, "count": 217 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.01499969494373848, "min": 0.010806223685358418, "max": 0.024950472956212857, "count": 217 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.11141383474071821, "min": 0.08322730089227358, "max": 0.12375405405958494, "count": 217 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.11141383474071821, "min": 0.08322730089227358, "max": 0.12375405405958494, "count": 217 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.1126241164902846, "min": 0.08392686496178309, "max": 0.12609628587961197, "count": 217 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.1126241164902846, "min": 0.08392686496178309, "max": 0.12609628587961197, "count": 217 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 217 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 217 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 217 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 217 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 217 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 217 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1706600704", "python_version": "3.10.12 | packaged by conda-forge | (main, Jun 23 2023, 22:34:57) [MSC v.1936 64 bit (AMD64)]", "command_line_arguments": "\\\\?\\C:\\Users\\tobil\\anaconda3\\envs\\rl\\Scripts\\mlagents-learn .\\ml-agents\\config\\poca\\SoccerTwos.yaml --env=.\\ml-agents\\training-envs-executables\\SoccerTwos.exe --run-id=SoccerTwo-second-try --no-graphics --resume", "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": "1706630414" }, "total": 29709.2995169, "count": 1, "self": 10.01248879999548, "children": { "run_training.setup": { "total": 0.147625000000005, "count": 1, "self": 0.147625000000005 }, "TrainerController.start_learning": { "total": 29699.1394031, "count": 1, "self": 14.508806899521005, "children": { "TrainerController._reset_env": { "total": 29.732691799999856, "count": 24, "self": 29.732691799999856 }, "TrainerController.advance": { "total": 29654.748855600483, "count": 312193, "self": 15.028372000248055, "children": { "env_step": { "total": 9861.239083399883, "count": 312193, "self": 7007.377935899409, "children": { "SubprocessEnvManager._take_step": { "total": 2845.1397851997517, "count": 312193, "self": 90.18912939865186, "children": { "TorchPolicy.evaluate": { "total": 2754.9506558011, "count": 563020, "self": 2754.9506558011 } } }, "workers": { "total": 8.721362300723115, "count": 312193, "self": 0.0, "children": { "worker_root": { "total": 29596.77368780052, "count": 312193, "is_parallel": true, "self": 24386.88798610206, "children": { "steps_from_proto": { "total": 0.0836177000034013, "count": 48, "is_parallel": true, "self": 0.01826350000715138, "children": { "_process_rank_one_or_two_observation": { "total": 0.06535419999624992, "count": 192, "is_parallel": true, "self": 0.06535419999624992 } } }, "UnityEnvironment.step": { "total": 5209.802083998454, "count": 312193, "is_parallel": true, "self": 294.29451889895245, "children": { "UnityEnvironment._generate_step_input": { "total": 288.06887059956597, "count": 312193, "is_parallel": true, "self": 288.06887059956597 }, "communicator.exchange": { "total": 3605.2846974999156, "count": 312193, "is_parallel": true, "self": 3605.2846974999156 }, "steps_from_proto": { "total": 1022.15399700002, "count": 624386, "is_parallel": true, "self": 232.03499170110297, "children": { "_process_rank_one_or_two_observation": { "total": 790.119005298917, "count": 2497544, "is_parallel": true, "self": 790.119005298917 } } } } } } } } } } }, "trainer_advance": { "total": 19778.48140020035, "count": 312193, "self": 101.48905000017112, "children": { "process_trajectory": { "total": 4005.1728540001513, "count": 312193, "self": 4002.7356836001486, "children": { "RLTrainer._checkpoint": { "total": 2.437170400002742, "count": 9, "self": 2.437170400002742 } } }, "_update_policy": { "total": 15671.819496200029, "count": 218, "self": 1489.4155575001005, "children": { "TorchPOCAOptimizer.update": { "total": 14182.403938699928, "count": 6537, "self": 14182.403938699928 } } } } } } }, "trainer_threads": { "total": 1.7999991541728377e-06, "count": 1, "self": 1.7999991541728377e-06 }, "TrainerController._save_models": { "total": 0.14904699999897275, "count": 1, "self": 0.012079399999493035, "children": { "RLTrainer._checkpoint": { "total": 0.13696759999947972, "count": 1, "self": 0.13696759999947972 } } } } } } }