{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 3.2765138149261475, "min": 3.275592565536499, "max": 3.295715808868408, "count": 5 }, "SoccerTwos.Policy.Entropy.sum": { "value": 62384.82421875, "min": 15619.82421875, "max": 105462.90625, "count": 5 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 859.25, "min": 798.0, "max": 907.1428571428571, "count": 5 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 13748.0, "min": 6796.0, "max": 30016.0, "count": 5 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1200.9758647909507, "min": 1200.72930853053, "max": 1201.4947322886426, "count": 5 }, "SoccerTwos.Self-play.ELO.sum": { "value": 2401.9517295819014, "min": 2401.9517295819014, "max": 7208.968393731856, "count": 5 }, "SoccerTwos.Step.mean": { "value": 49808.0, "min": 9026.0, "max": 49808.0, "count": 5 }, "SoccerTwos.Step.sum": { "value": 49808.0, "min": 9026.0, "max": 49808.0, "count": 5 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": 0.027342820540070534, "min": 0.027342820540070534, "max": 0.032734353095293045, "count": 5 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": 0.300771027803421, "min": 0.300771027803421, "max": 0.45823562145233154, "count": 5 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": 0.02600504644215107, "min": 0.02600504644215107, "max": 0.03275395929813385, "count": 5 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": 0.2860555052757263, "min": 0.2860555052757263, "max": 0.458451509475708, "count": 5 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 5 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 5 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.18181818181818182, "min": -0.25717142862933023, "max": 0.10719999795158704, "count": 5 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -2.0, "min": -3.600400000810623, "max": 1.2863999754190445, "count": 5 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.18181818181818182, "min": -0.25717142862933023, "max": 0.10719999795158704, "count": 5 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -2.0, "min": -3.600400000810623, "max": 1.2863999754190445, "count": 5 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 5 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 5 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.017365759436506777, "min": 0.015031918508705134, "max": 0.017365759436506777, "count": 2 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.017365759436506777, "min": 0.015031918508705134, "max": 0.017365759436506777, "count": 2 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.001899970720599716, "min": 0.001899970720599716, "max": 0.0029056487837806344, "count": 2 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.001899970720599716, "min": 0.001899970720599716, "max": 0.0029056487837806344, "count": 2 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.0019147462754820785, "min": 0.0019147462754820785, "max": 0.002423882899352182, "count": 2 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.0019147462754820785, "min": 0.0019147462754820785, "max": 0.002423882899352182, "count": 2 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 2 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 2 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000004, "max": 0.20000000000000007, "count": 2 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000004, "max": 0.20000000000000007, "count": 2 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 2 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 2 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1678392222", "python_version": "3.9.16 (main, Mar 8 2023, 10:39:24) [MSC v.1916 64 bit (AMD64)]", "command_line_arguments": "C:\\ProgramData\\Anaconda3\\envs\\rl\\Scripts\\mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.exe --run-id=SoccerTwos --no-graphics", "mlagents_version": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.13.1+cpu", "numpy_version": "1.21.2", "end_time_seconds": "1678392403" }, "total": 181.0464171, "count": 1, "self": 0.34392710000000193, "children": { "run_training.setup": { "total": 0.10022870000000017, "count": 1, "self": 0.10022870000000017 }, "TrainerController.start_learning": { "total": 180.6022613, "count": 1, "self": 0.07455710000007798, "children": { "TrainerController._reset_env": { "total": 4.0386272000000005, "count": 1, "self": 4.0386272000000005 }, "TrainerController.advance": { "total": 176.32984869999993, "count": 3610, "self": 0.08258590000136223, "children": { "env_step": { "total": 61.6917150999988, "count": 3610, "self": 47.841059299999365, "children": { "SubprocessEnvManager._take_step": { "total": 13.799688999999473, "count": 3610, "self": 0.5619133999996979, "children": { "TorchPolicy.evaluate": { "total": 13.237775599999775, "count": 7190, "self": 13.237775599999775 } } }, "workers": { "total": 0.05096679999996567, "count": 3610, "self": 0.0, "children": { "worker_root": { "total": 176.0347210999997, "count": 3610, "is_parallel": true, "self": 137.1491593, "children": { "steps_from_proto": { "total": 0.001895500000000716, "count": 2, "is_parallel": true, "self": 0.00043689999999951823, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014586000000011978, "count": 8, "is_parallel": true, "self": 0.0014586000000011978 } } }, "UnityEnvironment.step": { "total": 38.88366629999969, "count": 3610, "is_parallel": true, "self": 2.0254024000008357, "children": { "UnityEnvironment._generate_step_input": { "total": 1.5076870999999894, "count": 3610, "is_parallel": true, "self": 1.5076870999999894 }, "communicator.exchange": { "total": 28.993242199999717, "count": 3610, "is_parallel": true, "self": 28.993242199999717 }, "steps_from_proto": { "total": 6.357334599999148, "count": 7220, "is_parallel": true, "self": 1.275067899998806, "children": { "_process_rank_one_or_two_observation": { "total": 5.082266700000342, "count": 28880, "is_parallel": true, "self": 5.082266700000342 } } } } } } } } } } }, "trainer_advance": { "total": 114.55554769999975, "count": 3610, "self": 0.5550712999998098, "children": { "process_trajectory": { "total": 57.82772349999994, "count": 3610, "self": 57.82772349999994 }, "_update_policy": { "total": 56.17275289999999, "count": 2, "self": 7.2909501000001455, "children": { "TorchPOCAOptimizer.update": { "total": 48.881802799999846, "count": 69, "self": 48.881802799999846 } } } } } } }, "trainer_threads": { "total": 9.000000034120603e-07, "count": 1, "self": 9.000000034120603e-07 }, "TrainerController._save_models": { "total": 0.1592273999999918, "count": 1, "self": 0.0061725999999850956, "children": { "RLTrainer._checkpoint": { "total": 0.1530548000000067, "count": 1, "self": 0.1530548000000067 } } } } } } }