{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.7994298934936523, "min": 1.784654974937439, "max": 3.295724630355835, "count": 616 }, "SoccerTwos.Policy.Entropy.sum": { "value": 35815.8515625, "min": 22801.48828125, "max": 144439.0625, "count": 616 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 83.96551724137932, "min": 40.23770491803279, "max": 999.0, "count": 616 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19480.0, "min": 16532.0, "max": 23552.0, "count": 616 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1544.4499912357385, "min": 1187.1566745841485, "max": 1587.1553806467844, "count": 581 }, "SoccerTwos.Self-play.ELO.sum": { "value": 179156.19898334568, "min": 2378.2809550475304, "max": 367584.5202686837, "count": 581 }, "SoccerTwos.Step.mean": { "value": 6159916.0, "min": 9206.0, "max": 6159916.0, "count": 616 }, "SoccerTwos.Step.sum": { "value": 6159916.0, "min": 9206.0, "max": 6159916.0, "count": 616 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": 0.01978658325970173, "min": -0.14759381115436554, "max": 0.1493956297636032, "count": 616 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": 2.295243740081787, "min": -30.699512481689453, "max": 25.657739639282227, "count": 616 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": 0.019230442121624947, "min": -0.14938680827617645, "max": 0.15320727229118347, "count": 616 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": 2.230731248855591, "min": -31.07245635986328, "max": 26.35165023803711, "count": 616 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 616 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 616 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.10933793207694745, "min": -0.6666666666666666, "max": 0.38814857346670967, "count": 616 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -12.683200120925903, "min": -68.55400037765503, "max": 63.01439988613129, "count": 616 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.10933793207694745, "min": -0.6666666666666666, "max": 0.38814857346670967, "count": 616 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -12.683200120925903, "min": -68.55400037765503, "max": 63.01439988613129, "count": 616 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 616 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 616 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.014084834283373008, "min": 0.010017290062387474, "max": 0.024107007146812975, "count": 296 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.014084834283373008, "min": 0.010017290062387474, "max": 0.024107007146812975, "count": 296 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.08509936109185219, "min": 3.064193956940168e-06, "max": 0.12175564219554265, "count": 296 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.08509936109185219, "min": 3.064193956940168e-06, "max": 0.12175564219554265, "count": 296 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.08593981936573983, "min": 3.0190435306091484e-06, "max": 0.12396949579318364, "count": 296 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.08593981936573983, "min": 3.0190435306091484e-06, "max": 0.12396949579318364, "count": 296 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 296 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 296 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 296 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 296 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 296 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 296 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1707993115", "python_version": "3.10.12 | packaged by conda-forge | (main, Jun 23 2023, 22:34:57) [MSC v.1936 64 bit (AMD64)]", "command_line_arguments": "\\\\?\\C:\\Users\\WajidIQBAL\\anaconda3\\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": "2.2.0+cpu", "numpy_version": "1.23.5", "end_time_seconds": "1708005500" }, "total": 12385.6348667, "count": 1, "self": 0.4857663999991928, "children": { "run_training.setup": { "total": 0.06063380000000507, "count": 1, "self": 0.06063380000000507 }, "TrainerController.start_learning": { "total": 12385.088466500001, "count": 1, "self": 6.585726999135659, "children": { "TrainerController._reset_env": { "total": 6.884737899997617, "count": 31, "self": 6.884737899997617 }, "TrainerController.advance": { "total": 12371.525132200866, "count": 421350, "self": 6.878538901006323, "children": { "env_step": { "total": 4259.456805300052, "count": 421350, "self": 3322.310926299174, "children": { "SubprocessEnvManager._take_step": { "total": 932.8203095005636, "count": 421350, "self": 39.56607430120425, "children": { "TorchPolicy.evaluate": { "total": 893.2542351993593, "count": 780502, "self": 893.2542351993593 } } }, "workers": { "total": 4.325569500314714, "count": 421350, "self": 0.0, "children": { "worker_root": { "total": 12371.634103400815, "count": 421350, "is_parallel": true, "self": 9743.560618400781, "children": { "steps_from_proto": { "total": 0.034617800001569776, "count": 62, "is_parallel": true, "self": 0.006468000008226227, "children": { "_process_rank_one_or_two_observation": { "total": 0.02814979999334355, "count": 248, "is_parallel": true, "self": 0.02814979999334355 } } }, "UnityEnvironment.step": { "total": 2628.0388672000327, "count": 421350, "is_parallel": true, "self": 142.92145099948175, "children": { "UnityEnvironment._generate_step_input": { "total": 102.63063090013225, "count": 421350, "is_parallel": true, "self": 102.63063090013225 }, "communicator.exchange": { "total": 1951.7629908998983, "count": 421350, "is_parallel": true, "self": 1951.7629908998983 }, "steps_from_proto": { "total": 430.7237944005201, "count": 842700, "is_parallel": true, "self": 79.76688340053784, "children": { "_process_rank_one_or_two_observation": { "total": 350.95691099998226, "count": 3370800, "is_parallel": true, "self": 350.95691099998226 } } } } } } } } } } }, "trainer_advance": { "total": 8105.189787999808, "count": 421350, "self": 51.18202409964306, "children": { "process_trajectory": { "total": 978.3013134001662, "count": 421350, "self": 977.2305326001656, "children": { "RLTrainer._checkpoint": { "total": 1.070780800000648, "count": 12, "self": 1.070780800000648 } } }, "_update_policy": { "total": 7075.706450499998, "count": 296, "self": 587.3439546000136, "children": { "TorchPOCAOptimizer.update": { "total": 6488.362495899984, "count": 8880, "self": 6488.362495899984 } } } } } } }, "trainer_threads": { "total": 8.000006346264854e-07, "count": 1, "self": 8.000006346264854e-07 }, "TrainerController._save_models": { "total": 0.09286860000065644, "count": 1, "self": 0.0067882000003010035, "children": { "RLTrainer._checkpoint": { "total": 0.08608040000035544, "count": 1, "self": 0.08608040000035544 } } } } } } }