{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.4263981580734253, "min": 1.1614277362823486, "max": 1.475717544555664, "count": 3 }, "SoccerTwos.Policy.Entropy.sum": { "value": 27067.33203125, "min": 297.32550048828125, "max": 32064.390625, "count": 3 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 52.73626373626374, "min": 6.0, "max": 52.73626373626374, "count": 3 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19196.0, "min": 24.0, "max": 20076.0, "count": 3 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1194.9309115859849, "min": 1194.9309115859849, "max": 1202.9071597916536, "count": 3 }, "SoccerTwos.Self-play.ELO.sum": { "value": 217477.42590864922, "min": 2400.361516626417, "max": 230958.1746799975, "count": 3 }, "SoccerTwos.Step.mean": { "value": 16519973.0, "min": 16499994.0, "max": 16519973.0, "count": 3 }, "SoccerTwos.Step.sum": { "value": 16519973.0, "min": 16499994.0, "max": 16519973.0, "count": 3 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.035763125866651535, "min": -0.035763125866651535, "max": 0.047167740762233734, "count": 3 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -6.544651985168457, "min": -6.544651985168457, "max": 0.047167740762233734, "count": 3 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.03540819138288498, "min": -0.03540819138288498, "max": 0.047413524240255356, "count": 3 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -6.47969913482666, "min": -6.47969913482666, "max": 0.047413524240255356, "count": 3 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 3 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 3 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.21138579141898234, "min": -0.21138579141898234, "max": 0.9922000169754028, "count": 3 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -38.68359982967377, "min": -38.68359982967377, "max": 0.9922000169754028, "count": 3 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.21138579141898234, "min": -0.21138579141898234, "max": 0.9922000169754028, "count": 3 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -38.68359982967377, "min": -38.68359982967377, "max": 0.9922000169754028, "count": 3 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 3 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 3 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1681577525", "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\\Omars\\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": "1681577665" }, "total": 140.14690910000002, "count": 1, "self": 0.009547299999979941, "children": { "run_training.setup": { "total": 0.09421129999999955, "count": 1, "self": 0.09421129999999955 }, "TrainerController.start_learning": { "total": 140.04315050000002, "count": 1, "self": 0.04101269999975443, "children": { "TrainerController._reset_env": { "total": 3.2773194000000005, "count": 2, "self": 3.2773194000000005 }, "TrainerController.advance": { "total": 136.59137120000025, "count": 1486, "self": 0.04112180000035437, "children": { "env_step": { "total": 25.717278399999906, "count": 1486, "self": 20.513471000000187, "children": { "SubprocessEnvManager._take_step": { "total": 5.18007259999985, "count": 1486, "self": 0.1786386999999312, "children": { "TorchPolicy.evaluate": { "total": 5.001433899999919, "count": 2664, "self": 5.001433899999919 } } }, "workers": { "total": 0.023734799999866496, "count": 1486, "self": 0.0, "children": { "worker_root": { "total": 134.67871639999998, "count": 1486, "is_parallel": true, "self": 118.24266150000007, "children": { "steps_from_proto": { "total": 0.005688200000000254, "count": 4, "is_parallel": true, "self": 0.0011276999999996207, "children": { "_process_rank_one_or_two_observation": { "total": 0.0045605000000006335, "count": 16, "is_parallel": true, "self": 0.0045605000000006335 } } }, "UnityEnvironment.step": { "total": 16.430366699999915, "count": 1486, "is_parallel": true, "self": 0.797231399999971, "children": { "UnityEnvironment._generate_step_input": { "total": 0.683942099999987, "count": 1486, "is_parallel": true, "self": 0.683942099999987 }, "communicator.exchange": { "total": 12.451345200000185, "count": 1486, "is_parallel": true, "self": 12.451345200000185 }, "steps_from_proto": { "total": 2.4978479999997725, "count": 2972, "is_parallel": true, "self": 0.5280792999997752, "children": { "_process_rank_one_or_two_observation": { "total": 1.9697686999999973, "count": 11888, "is_parallel": true, "self": 1.9697686999999973 } } } } } } } } } } }, "trainer_advance": { "total": 110.83297099999999, "count": 1486, "self": 0.24486360000000218, "children": { "process_trajectory": { "total": 108.52994779999997, "count": 1486, "self": 108.25905219999997, "children": { "RLTrainer._checkpoint": { "total": 0.27089559999999935, "count": 1, "self": 0.27089559999999935 } } }, "_update_policy": { "total": 2.0581596000000104, "count": 1, "self": 1.0602689000000112, "children": { "TorchPOCAOptimizer.update": { "total": 0.9978906999999992, "count": 1, "self": 0.9978906999999992 } } } } } } }, "trainer_threads": { "total": 1.3000000080864993e-06, "count": 1, "self": 1.3000000080864993e-06 }, "TrainerController._save_models": { "total": 0.13344589999999812, "count": 1, "self": 0.0029365999999981796, "children": { "RLTrainer._checkpoint": { "total": 0.13050929999999994, "count": 1, "self": 0.13050929999999994 } } } } } } }