{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 2.260557174682617, "min": 2.260557174682617, "max": 3.2957239151000977, "count": 564 }, "SoccerTwos.Policy.Entropy.sum": { "value": 46368.546875, "min": 14733.5625, "max": 109877.9609375, "count": 564 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 45.691588785046726, "min": 44.40909090909091, "max": 999.0, "count": 564 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19556.0, "min": 15984.0, "max": 24856.0, "count": 564 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1494.1635052358674, "min": 1195.220031299549, "max": 1513.1711619136317, "count": 420 }, "SoccerTwos.Self-play.ELO.sum": { "value": 319750.99012047565, "min": 2390.4575313710816, "max": 331833.77359809185, "count": 420 }, "SoccerTwos.Step.mean": { "value": 5639978.0, "min": 9446.0, "max": 5639978.0, "count": 564 }, "SoccerTwos.Step.sum": { "value": 5639978.0, "min": 9446.0, "max": 5639978.0, "count": 564 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.05026876553893089, "min": -0.10771407186985016, "max": 0.19884932041168213, "count": 564 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -10.757515907287598, "min": -18.203678131103516, "max": 29.288837432861328, "count": 564 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.05486476793885231, "min": -0.10148370265960693, "max": 0.19832168519496918, "count": 564 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -11.741060256958008, "min": -17.150745391845703, "max": 29.84763526916504, "count": 564 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 564 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 564 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.14337476586627068, "min": -0.45059166569262743, "max": 0.5582567133120636, "count": 564 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -30.682199895381927, "min": -33.76479995250702, "max": 68.83200007677078, "count": 564 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.14337476586627068, "min": -0.45059166569262743, "max": 0.5582567133120636, "count": 564 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -30.682199895381927, "min": -33.76479995250702, "max": 68.83200007677078, "count": 564 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 564 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 564 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.017983886908405113, "min": 0.011172140129042418, "max": 0.02473271309863776, "count": 265 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.017983886908405113, "min": 0.011172140129042418, "max": 0.02473271309863776, "count": 265 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.10779028882582982, "min": 1.4966541759993863e-07, "max": 0.10779028882582982, "count": 265 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.10779028882582982, "min": 1.4966541759993863e-07, "max": 0.10779028882582982, "count": 265 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.10997362807393074, "min": 1.6504089686009138e-07, "max": 0.10997362807393074, "count": 265 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.10997362807393074, "min": 1.6504089686009138e-07, "max": 0.10997362807393074, "count": 265 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 265 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 265 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 265 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 265 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 265 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 265 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1714558820", "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\\Ming\\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": "2.3.0+cpu", "numpy_version": "1.23.5", "end_time_seconds": "1714585314" }, "total": 26494.325880800025, "count": 1, "self": 0.3515620001126081, "children": { "run_training.setup": { "total": 0.12783819995820522, "count": 1, "self": 0.12783819995820522 }, "TrainerController.start_learning": { "total": 26493.846480599954, "count": 1, "self": 15.142953247530386, "children": { "TrainerController._reset_env": { "total": 7.077135700383224, "count": 29, "self": 7.077135700383224 }, "TrainerController.advance": { "total": 26471.34476205206, "count": 371560, "self": 15.971983115072362, "children": { "env_step": { "total": 11853.994336954202, "count": 371560, "self": 9123.942751222407, "children": { "SubprocessEnvManager._take_step": { "total": 2720.2494692602195, "count": 371560, "self": 93.85542461054865, "children": { "TorchPolicy.evaluate": { "total": 2626.394044649671, "count": 721924, "self": 2626.394044649671 } } }, "workers": { "total": 9.802116471575573, "count": 371559, "self": 0.0, "children": { "worker_root": { "total": 26470.445845735725, "count": 371559, "is_parallel": true, "self": 19281.97781156737, "children": { "steps_from_proto": { "total": 0.09126840042881668, "count": 58, "is_parallel": true, "self": 0.018107699928805232, "children": { "_process_rank_one_or_two_observation": { "total": 0.07316070050001144, "count": 232, "is_parallel": true, "self": 0.07316070050001144 } } }, "UnityEnvironment.step": { "total": 7188.376765767927, "count": 371559, "is_parallel": true, "self": 422.21167455415707, "children": { "UnityEnvironment._generate_step_input": { "total": 382.7443088013679, "count": 371559, "is_parallel": true, "self": 382.7443088013679 }, "communicator.exchange": { "total": 5024.593184787082, "count": 371559, "is_parallel": true, "self": 5024.593184787082 }, "steps_from_proto": { "total": 1358.8275976253208, "count": 743118, "is_parallel": true, "self": 257.7448606932303, "children": { "_process_rank_one_or_two_observation": { "total": 1101.0827369320905, "count": 2972472, "is_parallel": true, "self": 1101.0827369320905 } } } } } } } } } } }, "trainer_advance": { "total": 14601.378441982786, "count": 371559, "self": 100.0309511461528, "children": { "process_trajectory": { "total": 2123.7640666377265, "count": 371559, "self": 2121.113498437451, "children": { "RLTrainer._checkpoint": { "total": 2.650568200275302, "count": 11, "self": 2.650568200275302 } } }, "_update_policy": { "total": 12377.583424198907, "count": 265, "self": 1139.5232217991725, "children": { "TorchPOCAOptimizer.update": { "total": 11238.060202399734, "count": 7950, "self": 11238.060202399734 } } } } } } }, "trainer_threads": { "total": 2.600019797682762e-06, "count": 1, "self": 2.600019797682762e-06 }, "TrainerController._save_models": { "total": 0.28162699996028095, "count": 1, "self": 0.015209099976345897, "children": { "RLTrainer._checkpoint": { "total": 0.26641789998393506, "count": 1, "self": 0.26641789998393506 } } } } } } }