{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.0099631547927856, "min": 0.8813402056694031, "max": 3.1872897148132324, "count": 54 }, "SoccerTwos.Policy.Entropy.sum": { "value": 404017.59375, "min": 353805.21875, "max": 1314387.25, "count": 54 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 83.83361629881155, "min": 58.11577082102776, "max": 955.1619047619048, "count": 54 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 395024.0, "min": 393148.0, "max": 403432.0, "count": 54 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1664.5431958897066, "min": 1195.104878128798, "max": 1670.6613498713052, "count": 54 }, "SoccerTwos.Self-play.ELO.sum": { "value": 3921663.7695161486, "min": 11970.46904662211, "max": 5509092.773048887, "count": 54 }, "SoccerTwos.Step.mean": { "value": 10799992.0, "min": 199034.0, "max": 10799992.0, "count": 54 }, "SoccerTwos.Step.sum": { "value": 10799992.0, "min": 199034.0, "max": 10799992.0, "count": 54 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.06383835524320602, "min": -0.4753003716468811, "max": 0.24938221275806427, "count": 54 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -150.40316772460938, "min": -221.7964324951172, "max": 648.6431274414062, "count": 54 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.0635887011885643, "min": -0.47427868843078613, "max": 0.24749551713466644, "count": 54 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -149.81497192382812, "min": -216.04910278320312, "max": 643.73583984375, "count": 54 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 54 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 54 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.07190543286666805, "min": -0.10928071734616575, "max": 0.334051210689618, "count": 54 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -169.40919983386993, "min": -227.53519892692566, "max": 868.8671990036964, "count": 54 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.07190543286666805, "min": -0.10928071734616575, "max": 0.334051210689618, "count": 54 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -169.40919983386993, "min": -227.53519892692566, "max": 868.8671990036964, "count": 54 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.020784668495198277, "min": 0.016045359763666056, "max": 0.022222726202259464, "count": 54 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.20784668495198277, "min": 0.1444082378729945, "max": 0.2157391439975413, "count": 54 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.08462687980383635, "min": 0.00037273440600241517, "max": 0.11116952544078232, "count": 54 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.8462687980383634, "min": 0.0037273440600241515, "max": 1.1116952544078231, "count": 54 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.0865291686169803, "min": 0.00037326813529119817, "max": 0.11431066671386363, "count": 54 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.865291686169803, "min": 0.0037326813529119816, "max": 1.1431066671386363, "count": 54 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0005000000000000001, "min": 0.0005, "max": 0.0005000000000000001, "count": 54 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.005000000000000001, "min": 0.0045000000000000005, "max": 0.005000000000000001, "count": 54 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.3358328104, "min": 0.3358328104, "max": 0.3993619013333334, "count": 54 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 3.358328104, "min": 3.0330983280000003, "max": 3.9579867640000006, "count": 54 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.004999999999999999, "min": 0.004999999999999999, "max": 0.005000000000000001, "count": 54 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.049999999999999996, "min": 0.045, "max": 0.05, "count": 54 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 54 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 54 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1725045213", "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\\luca\\miniconda3\\envs\\mlagents\\Scripts\\mlagents-learn ./config/poca/SoccerTwosV2.yaml --env=./training-envs-executables/SoccerTwos.exe --run-id=SoccerTwosV2 --no-graphics", "mlagents_version": "1.0.0", "mlagents_envs_version": "1.0.0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.2.2+cu121", "numpy_version": "1.23.3", "end_time_seconds": "1725066253" }, "total": 21040.00885079999, "count": 1, "self": 0.1393313999287784, "children": { "run_training.setup": { "total": 0.12158450006972998, "count": 1, "self": 0.12158450006972998 }, "TrainerController.start_learning": { "total": 21039.74793489999, "count": 1, "self": 13.432928950176574, "children": { "TrainerController._reset_env": { "total": 7.23699939972721, "count": 55, "self": 7.23699939972721 }, "TrainerController.advance": { "total": 21018.872226050124, "count": 734287, "self": 14.724991813185625, "children": { "env_step": { "total": 15334.720410231734, "count": 734287, "self": 8210.495862750453, "children": { "SubprocessEnvManager._take_step": { "total": 7115.160639468464, "count": 734288, "self": 92.968986197724, "children": { "TorchPolicy.evaluate": { "total": 7022.19165327074, "count": 1384753, "self": 7022.19165327074 } } }, "workers": { "total": 9.063908012816682, "count": 734286, "self": 0.0, "children": { "worker_root": { "total": 21001.55712337722, "count": 734286, "is_parallel": true, "self": 14487.069124733913, "children": { "steps_from_proto": { "total": 0.07036890112794936, "count": 112, "is_parallel": true, "self": 0.014784600702114403, "children": { "_process_rank_one_or_two_observation": { "total": 0.055584300425834954, "count": 448, "is_parallel": true, "self": 0.055584300425834954 } } }, "UnityEnvironment.step": { "total": 6514.41762974218, "count": 734286, "is_parallel": true, "self": 340.42675854521804, "children": { "UnityEnvironment._generate_step_input": { "total": 302.8740334486356, "count": 734286, "is_parallel": true, "self": 302.8740334486356 }, "communicator.exchange": { "total": 4759.800506798434, "count": 734286, "is_parallel": true, "self": 4759.800506798434 }, "steps_from_proto": { "total": 1111.3163309498923, "count": 1468572, "is_parallel": true, "self": 230.99577964982018, "children": { "_process_rank_one_or_two_observation": { "total": 880.3205513000721, "count": 5874288, "is_parallel": true, "self": 880.3205513000721 } } } } } } } } } } }, "trainer_advance": { "total": 5669.426824005204, "count": 734286, "self": 102.61182564555202, "children": { "process_trajectory": { "total": 2417.0267778587295, "count": 734286, "self": 2413.619485358824, "children": { "RLTrainer._checkpoint": { "total": 3.407292499905452, "count": 21, "self": 3.407292499905452 } } }, "_update_policy": { "total": 3149.7882205009228, "count": 521, "self": 1580.444263005862, "children": { "TorchPOCAOptimizer.update": { "total": 1569.3439574950607, "count": 20868, "self": 1569.3439574950607 } } } } } } }, "trainer_threads": { "total": 9.00006853044033e-07, "count": 1, "self": 9.00006853044033e-07 }, "TrainerController._save_models": { "total": 0.2057795999571681, "count": 1, "self": 0.005418600048869848, "children": { "RLTrainer._checkpoint": { "total": 0.20036099990829825, "count": 1, "self": 0.20036099990829825 } } } } } } }