{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.890148401260376, "min": 1.8000892400741577, "max": 3.295700788497925, "count": 661 }, "SoccerTwos.Policy.Entropy.sum": { "value": 40403.8125, "min": 15318.3759765625, "max": 112297.6015625, "count": 661 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 52.60215053763441, "min": 44.018181818181816, "max": 999.0, "count": 661 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19568.0, "min": 15820.0, "max": 27780.0, "count": 661 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1654.5920843043043, "min": 1188.6033551828798, "max": 1659.2440250225488, "count": 635 }, "SoccerTwos.Self-play.ELO.sum": { "value": 307754.1276806006, "min": 2378.999706313095, "max": 350028.9295997743, "count": 635 }, "SoccerTwos.Step.mean": { "value": 6609933.0, "min": 9914.0, "max": 6609933.0, "count": 661 }, "SoccerTwos.Step.sum": { "value": 6609933.0, "min": 9914.0, "max": 6609933.0, "count": 661 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.037915363907814026, "min": -0.12990498542785645, "max": 0.17771191895008087, "count": 661 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -7.09017276763916, "min": -21.694133758544922, "max": 32.14956283569336, "count": 661 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.040252067148685455, "min": -0.12771138548851013, "max": 0.1778380274772644, "count": 661 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -7.52713680267334, "min": -21.327800750732422, "max": 32.368892669677734, "count": 661 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 661 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 661 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": 0.01557647098194469, "min": -0.5913999974727631, "max": 0.4990888833999634, "count": 661 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 2.9128000736236572, "min": -50.884800016880035, "max": 58.565199851989746, "count": 661 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.01557647098194469, "min": -0.5913999974727631, "max": 0.4990888833999634, "count": 661 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 2.9128000736236572, "min": -50.884800016880035, "max": 58.565199851989746, "count": 661 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 661 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 661 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.01665187176258769, "min": 0.008899209591618273, "max": 0.024064077405879895, "count": 317 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.01665187176258769, "min": 0.008899209591618273, "max": 0.024064077405879895, "count": 317 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.10776285429795583, "min": 7.0393187343142925e-06, "max": 0.1203782210747401, "count": 317 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.10776285429795583, "min": 7.0393187343142925e-06, "max": 0.1203782210747401, "count": 317 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.10968858376145363, "min": 9.037535164679866e-06, "max": 0.12168711423873901, "count": 317 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.10968858376145363, "min": 9.037535164679866e-06, "max": 0.12168711423873901, "count": 317 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 317 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 317 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 317 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 317 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 317 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 317 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1697143801", "python_version": "3.10.11 | packaged by Anaconda, Inc. | (main, May 16 2023, 00:55:32) [MSC v.1916 64 bit (AMD64)]", "command_line_arguments": "\\\\?\\C:\\Users\\Bradfo\\anaconda3\\envs\\rlfinal\\Scripts\\mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.exe --run-id=SoccerTwos0 --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.1.0+cpu", "numpy_version": "1.23.5", "end_time_seconds": "1697174844" }, "total": 31042.1435117, "count": 1, "self": 7.268960000001243, "children": { "run_training.setup": { "total": 1.65054629999986, "count": 1, "self": 1.65054629999986 }, "TrainerController.start_learning": { "total": 31033.2240054, "count": 1, "self": 17.962819199725345, "children": { "TrainerController._reset_env": { "total": 108.77713449999692, "count": 34, "self": 108.77713449999692 }, "TrainerController.advance": { "total": 30902.521078900278, "count": 448616, "self": 18.379322501259594, "children": { "env_step": { "total": 13609.715683199254, "count": 448616, "self": 10538.369231900047, "children": { "SubprocessEnvManager._take_step": { "total": 3060.3185754992287, "count": 448616, "self": 98.26607039848614, "children": { "TorchPolicy.evaluate": { "total": 2962.0525051007426, "count": 834814, "self": 2962.0525051007426 } } }, "workers": { "total": 11.027875799977664, "count": 448615, "self": 0.0, "children": { "worker_root": { "total": 30942.692315299282, "count": 448615, "is_parallel": true, "self": 22576.61928259922, "children": { "steps_from_proto": { "total": 0.6648728999980449, "count": 68, "is_parallel": true, "self": 0.03666859999339067, "children": { "_process_rank_one_or_two_observation": { "total": 0.6282043000046542, "count": 272, "is_parallel": true, "self": 0.6282043000046542 } } }, "UnityEnvironment.step": { "total": 8365.408159800065, "count": 448615, "is_parallel": true, "self": 378.9986835017444, "children": { "UnityEnvironment._generate_step_input": { "total": 345.17941700000983, "count": 448615, "is_parallel": true, "self": 345.17941700000983 }, "communicator.exchange": { "total": 6331.366179499399, "count": 448615, "is_parallel": true, "self": 6331.366179499399 }, "steps_from_proto": { "total": 1309.863879798912, "count": 897230, "is_parallel": true, "self": 280.09605469589815, "children": { "_process_rank_one_or_two_observation": { "total": 1029.7678251030138, "count": 3588920, "is_parallel": true, "self": 1029.7678251030138 } } } } } } } } } } }, "trainer_advance": { "total": 17274.426073199764, "count": 448615, "self": 119.53171920014574, "children": { "process_trajectory": { "total": 3749.1029767996038, "count": 448615, "self": 3738.4807147995984, "children": { "RLTrainer._checkpoint": { "total": 10.622262000005321, "count": 13, "self": 10.622262000005321 } } }, "_update_policy": { "total": 13405.791377200014, "count": 317, "self": 1383.3851275000652, "children": { "TorchPOCAOptimizer.update": { "total": 12022.406249699949, "count": 9510, "self": 12022.406249699949 } } } } } } }, "trainer_threads": { "total": 2.0000006770715117e-06, "count": 1, "self": 2.0000006770715117e-06 }, "TrainerController._save_models": { "total": 3.9629707999993116, "count": 1, "self": 0.05022530000132974, "children": { "RLTrainer._checkpoint": { "total": 3.912745499997982, "count": 1, "self": 3.912745499997982 } } } } } } }