{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.9570204019546509, "min": 1.9343773126602173, "max": 3.295746088027954, "count": 345 }, "SoccerTwos.Policy.Entropy.sum": { "value": 36823.296875, "min": 8203.974609375, "max": 117514.0546875, "count": 345 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 71.21739130434783, "min": 42.08620689655172, "max": 999.0, "count": 345 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19656.0, "min": 3996.0, "max": 31452.0, "count": 345 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1553.8124313206704, "min": 1195.0758392557295, "max": 1576.8404164349931, "count": 340 }, "SoccerTwos.Self-play.ELO.sum": { "value": 214426.1155222525, "min": 2390.151678511459, "max": 361013.56374995445, "count": 340 }, "SoccerTwos.Step.mean": { "value": 3449919.0, "min": 9744.0, "max": 3449919.0, "count": 345 }, "SoccerTwos.Step.sum": { "value": 3449919.0, "min": 9744.0, "max": 3449919.0, "count": 345 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.04013489559292793, "min": -0.07595100998878479, "max": 0.19094324111938477, "count": 345 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -5.538615703582764, "min": -13.15078353881836, "max": 27.43212127685547, "count": 345 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.045506782829761505, "min": -0.08057396858930588, "max": 0.1898651123046875, "count": 345 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -6.279935836791992, "min": -14.825610160827637, "max": 27.314037322998047, "count": 345 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 345 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 345 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.11474347892014877, "min": -0.5080499991774559, "max": 0.4875208344310522, "count": 345 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -15.83460009098053, "min": -53.75280010700226, "max": 58.19000029563904, "count": 345 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.11474347892014877, "min": -0.5080499991774559, "max": 0.4875208344310522, "count": 345 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -15.83460009098053, "min": -53.75280010700226, "max": 58.19000029563904, "count": 345 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 345 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 345 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.014121736674011724, "min": 0.011251415135726953, "max": 0.024424244975671174, "count": 166 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.014121736674011724, "min": 0.011251415135726953, "max": 0.024424244975671174, "count": 166 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.10300621017813683, "min": 0.0008304478940165912, "max": 0.12439776758352915, "count": 166 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.10300621017813683, "min": 0.0008304478940165912, "max": 0.12439776758352915, "count": 166 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.10415177519122759, "min": 0.000824070256203413, "max": 0.12655389656623203, "count": 166 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.10415177519122759, "min": 0.000824070256203413, "max": 0.12655389656623203, "count": 166 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 166 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 166 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000004, "max": 0.20000000000000007, "count": 166 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000004, "max": 0.20000000000000007, "count": 166 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 166 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 166 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1716214895", "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:\\Programming\\Anaconda\\envs\\rl\\Scripts\\mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.exe --run-id=SoccerTwos --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.3.0+cpu", "numpy_version": "1.23.5", "end_time_seconds": "1716229238" }, "total": 14343.405976699985, "count": 1, "self": 0.33416739996755496, "children": { "run_training.setup": { "total": 0.14068520002183504, "count": 1, "self": 0.14068520002183504 }, "TrainerController.start_learning": { "total": 14342.931124099996, "count": 1, "self": 6.827881407021778, "children": { "TrainerController._reset_env": { "total": 8.31276689999504, "count": 18, "self": 8.31276689999504 }, "TrainerController.advance": { "total": 14327.57910279298, "count": 235036, "self": 6.421814991655992, "children": { "env_step": { "total": 5042.428487199213, "count": 235036, "self": 3943.1594364810153, "children": { "SubprocessEnvManager._take_step": { "total": 1094.9635137108562, "count": 235036, "self": 44.598583820828935, "children": { "TorchPolicy.evaluate": { "total": 1050.3649298900273, "count": 434380, "self": 1050.3649298900273 } } }, "workers": { "total": 4.305537007341627, "count": 235035, "self": 0.0, "children": { "worker_root": { "total": 14328.377224602824, "count": 235035, "is_parallel": true, "self": 11227.627575801482, "children": { "steps_from_proto": { "total": 0.037452599965035915, "count": 36, "is_parallel": true, "self": 0.007069700048305094, "children": { "_process_rank_one_or_two_observation": { "total": 0.03038289991673082, "count": 144, "is_parallel": true, "self": 0.03038289991673082 } } }, "UnityEnvironment.step": { "total": 3100.712196201377, "count": 235035, "is_parallel": true, "self": 183.86348560912302, "children": { "UnityEnvironment._generate_step_input": { "total": 219.3428394010698, "count": 235035, "is_parallel": true, "self": 219.3428394010698 }, "communicator.exchange": { "total": 2192.8369953949295, "count": 235035, "is_parallel": true, "self": 2192.8369953949295 }, "steps_from_proto": { "total": 504.6688757962547, "count": 470070, "is_parallel": true, "self": 96.13699782348704, "children": { "_process_rank_one_or_two_observation": { "total": 408.5318779727677, "count": 1880280, "is_parallel": true, "self": 408.5318779727677 } } } } } } } } } } }, "trainer_advance": { "total": 9278.728800602112, "count": 235035, "self": 51.284025008324534, "children": { "process_trajectory": { "total": 3920.6790171939065, "count": 235035, "self": 3919.8113520939078, "children": { "RLTrainer._checkpoint": { "total": 0.8676650999987032, "count": 6, "self": 0.8676650999987032 } } }, "_update_policy": { "total": 5306.765758399881, "count": 166, "self": 683.6224011009035, "children": { "TorchPOCAOptimizer.update": { "total": 4623.143357298977, "count": 4989, "self": 4623.143357298977 } } } } } } }, "trainer_threads": { "total": 2.4999899324029684e-06, "count": 1, "self": 2.4999899324029684e-06 }, "TrainerController._save_models": { "total": 0.2113705000083428, "count": 1, "self": 0.010710100003052503, "children": { "RLTrainer._checkpoint": { "total": 0.20066040000529028, "count": 1, "self": 0.20066040000529028 } } } } } } }