{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.8236401081085205, "min": 1.816789984703064, "max": 3.2957539558410645, "count": 542 }, "SoccerTwos.Policy.Entropy.sum": { "value": 36414.4453125, "min": 17382.8515625, "max": 106336.59375, "count": 542 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 57.96470588235294, "min": 44.81651376146789, "max": 999.0, "count": 542 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19708.0, "min": 15984.0, "max": 24368.0, "count": 542 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1600.8162501543295, "min": 1202.5799518752465, "max": 1612.1312020510723, "count": 536 }, "SoccerTwos.Self-play.ELO.sum": { "value": 272138.762526236, "min": 2409.3842854206932, "max": 342556.84415041376, "count": 536 }, "SoccerTwos.Step.mean": { "value": 5419987.0, "min": 9202.0, "max": 5419987.0, "count": 542 }, "SoccerTwos.Step.sum": { "value": 5419987.0, "min": 9202.0, "max": 5419987.0, "count": 542 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": 0.009928393177688122, "min": -0.1049918532371521, "max": 0.18253982067108154, "count": 542 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": 1.6878268718719482, "min": -16.2851505279541, "max": 25.03551483154297, "count": 542 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": 0.014193202368915081, "min": -0.10672014206647873, "max": 0.1740785837173462, "count": 542 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": 2.41284441947937, "min": -17.065570831298828, "max": 24.605972290039062, "count": 542 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 542 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 542 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": 0.02713294169482063, "min": -0.5833333333333334, "max": 0.6075979586766691, "count": 542 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 4.612600088119507, "min": -53.564000248909, "max": 72.31839990615845, "count": 542 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.02713294169482063, "min": -0.5833333333333334, "max": 0.6075979586766691, "count": 542 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 4.612600088119507, "min": -53.564000248909, "max": 72.31839990615845, "count": 542 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 542 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 542 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.015720353148693297, "min": 0.011549799980518098, "max": 0.024669724563136698, "count": 260 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.015720353148693297, "min": 0.011549799980518098, "max": 0.024669724563136698, "count": 260 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.09480199714501698, "min": 0.00014383122373449927, "max": 0.12502698227763176, "count": 260 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.09480199714501698, "min": 0.00014383122373449927, "max": 0.12502698227763176, "count": 260 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.09643616129954656, "min": 0.00014710981534638752, "max": 0.12777931094169617, "count": 260 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.09643616129954656, "min": 0.00014710981534638752, "max": 0.12777931094169617, "count": 260 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 260 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 260 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000004, "max": 0.20000000000000007, "count": 260 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000004, "max": 0.20000000000000007, "count": 260 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 260 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 260 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1705133508", "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\\karth\\anaconda3\\envs\\rl\\Scripts\\mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.exe --run-id=SoccerTwos --no-graphics --force", "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": "1705150124" }, "total": 16617.011633299997, "count": 1, "self": 4.2295673999906285, "children": { "run_training.setup": { "total": 0.07817600000271341, "count": 1, "self": 0.07817600000271341 }, "TrainerController.start_learning": { "total": 16612.703889900004, "count": 1, "self": 11.447416600472934, "children": { "TrainerController._reset_env": { "total": 4.540296700019098, "count": 28, "self": 4.540296700019098 }, "TrainerController.advance": { "total": 16596.522686399505, "count": 369636, "self": 11.744608300512482, "children": { "env_step": { "total": 7099.750584297573, "count": 369636, "self": 5413.150237094487, "children": { "SubprocessEnvManager._take_step": { "total": 1679.5166994022293, "count": 369636, "self": 64.66714889794093, "children": { "TorchPolicy.evaluate": { "total": 1614.8495505042883, "count": 685802, "self": 1614.8495505042883 } } }, "workers": { "total": 7.083647800856852, "count": 369635, "self": 0.0, "children": { "worker_root": { "total": 16594.738982003495, "count": 369635, "is_parallel": true, "self": 12384.536784907097, "children": { "steps_from_proto": { "total": 0.04792250000900822, "count": 56, "is_parallel": true, "self": 0.010319100074411836, "children": { "_process_rank_one_or_two_observation": { "total": 0.03760339993459638, "count": 224, "is_parallel": true, "self": 0.03760339993459638 } } }, "UnityEnvironment.step": { "total": 4210.154274596389, "count": 369635, "is_parallel": true, "self": 209.84940049712895, "children": { "UnityEnvironment._generate_step_input": { "total": 183.11874929901387, "count": 369635, "is_parallel": true, "self": 183.11874929901387 }, "communicator.exchange": { "total": 3168.7093459001335, "count": 369635, "is_parallel": true, "self": 3168.7093459001335 }, "steps_from_proto": { "total": 648.4767789001125, "count": 739270, "is_parallel": true, "self": 136.11069480020524, "children": { "_process_rank_one_or_two_observation": { "total": 512.3660840999073, "count": 2957080, "is_parallel": true, "self": 512.3660840999073 } } } } } } } } } } }, "trainer_advance": { "total": 9485.027493801419, "count": 369635, "self": 85.1049199026238, "children": { "process_trajectory": { "total": 1673.9583995988505, "count": 369635, "self": 1672.38175119886, "children": { "RLTrainer._checkpoint": { "total": 1.5766483999905176, "count": 10, "self": 1.5766483999905176 } } }, "_update_policy": { "total": 7725.964174299945, "count": 261, "self": 1030.1647698001543, "children": { "TorchPOCAOptimizer.update": { "total": 6695.79940449979, "count": 7839, "self": 6695.79940449979 } } } } } } }, "trainer_threads": { "total": 2.1000014385208488e-06, "count": 1, "self": 2.1000014385208488e-06 }, "TrainerController._save_models": { "total": 0.19348810000519734, "count": 1, "self": 0.013423200012766756, "children": { "RLTrainer._checkpoint": { "total": 0.18006489999243058, "count": 1, "self": 0.18006489999243058 } } } } } } }