{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.1111496686935425, "min": 1.1111496686935425, "max": 3.2737064361572266, "count": 140 }, "SoccerTwos.Policy.Entropy.sum": { "value": 111612.765625, "min": 110508.125, "max": 380168.96875, "count": 140 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 69.36974789915966, "min": 67.05177111716621, "max": 939.1538461538462, "count": 140 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 99060.0, "min": 95652.0, "max": 103312.0, "count": 140 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1620.0112989184006, "min": 1198.1827098176377, "max": 1624.1894708270681, "count": 140 }, "SoccerTwos.Self-play.ELO.sum": { "value": 1156688.067427738, "min": 4793.2610647804995, "max": 1175263.0834165935, "count": 140 }, "SoccerTwos.Step.mean": { "value": 6999958.0, "min": 49368.0, "max": 6999958.0, "count": 140 }, "SoccerTwos.Step.sum": { "value": 6999958.0, "min": 49368.0, "max": 6999958.0, "count": 140 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.01854032836854458, "min": -0.0850742906332016, "max": 0.18131530284881592, "count": 140 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -13.219253540039062, "min": -54.193031311035156, "max": 81.95451354980469, "count": 140 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.01944023370742798, "min": -0.09013748168945312, "max": 0.18171048164367676, "count": 140 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -13.860886573791504, "min": -56.44042205810547, "max": 82.13314056396484, "count": 140 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 140 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 140 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": 0.04991304422996489, "min": -0.14181917824157297, "max": 0.3555840008854866, "count": 140 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 35.588000535964966, "min": -85.3135998249054, "max": 88.89600022137165, "count": 140 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.04991304422996489, "min": -0.14181917824157297, "max": 0.3555840008854866, "count": 140 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 35.588000535964966, "min": -85.3135998249054, "max": 88.89600022137165, "count": 140 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.017009093132801353, "min": 0.016676689825956905, "max": 0.038463993404099416, "count": 140 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.034018186265602705, "min": 0.03381389796035364, "max": 0.11539198021229824, "count": 140 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.09284576013684273, "min": 0.0006058299935345228, "max": 0.09538967862725257, "count": 140 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.18569152027368546, "min": 0.0017943214339902625, "max": 0.28615084499120713, "count": 140 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.09270931206643582, "min": 0.0007139226215076632, "max": 0.0956115986406803, "count": 140 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.18541862413287163, "min": 0.001950476081110537, "max": 0.2868347959220409, "count": 140 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 1.8214567785857097e-06, "min": 1.8214567785857097e-06, "max": 0.0004977067147443714, "count": 140 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 3.6429135571714194e-06, "min": 3.6429135571714194e-06, "max": 0.0014725147197827714, "count": 140 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.10036427142857145, "min": 0.10036427142857145, "max": 0.19954134285714287, "count": 140 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.2007285428571429, "min": 0.2007285428571429, "max": 0.5945029428571429, "count": 140 }, "SoccerTwos.Policy.Beta.mean": { "value": 2.8177144285714247e-05, "min": 2.8177144285714247e-05, "max": 0.004977113008571428, "count": 140 }, "SoccerTwos.Policy.Beta.sum": { "value": 5.6354288571428495e-05, "min": 5.6354288571428495e-05, "max": 0.014725696848571428, "count": 140 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 140 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 140 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1710029953", "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\\ThinkPad\\miniconda3\\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": "2.2.1+cpu", "numpy_version": "1.22.3", "end_time_seconds": "1710092643" }, "total": 62690.205816400005, "count": 1, "self": 1.5007168000156526, "children": { "run_training.setup": { "total": 0.2303831999997783, "count": 1, "self": 0.2303831999997783 }, "TrainerController.start_learning": { "total": 62688.47471639999, "count": 1, "self": 15.482313503540354, "children": { "TrainerController._reset_env": { "total": 14.328854400015189, "count": 35, "self": 14.328854400015189 }, "TrainerController.advance": { "total": 62658.390361796424, "count": 470579, "self": 16.80483680150064, "children": { "env_step": { "total": 13982.906283896229, "count": 470579, "self": 10639.312883600187, "children": { "SubprocessEnvManager._take_step": { "total": 3333.282808997774, "count": 470579, "self": 111.35021650398812, "children": { "TorchPolicy.evaluate": { "total": 3221.9325924937857, "count": 883156, "self": 3221.9325924937857 } } }, "workers": { "total": 10.310591298268264, "count": 470579, "self": 0.0, "children": { "worker_root": { "total": 62650.755524501685, "count": 470579, "is_parallel": true, "self": 54088.76279749896, "children": { "steps_from_proto": { "total": 0.11634059997959412, "count": 70, "is_parallel": true, "self": 0.03372089993354166, "children": { "_process_rank_one_or_two_observation": { "total": 0.08261970004605246, "count": 280, "is_parallel": true, "self": 0.08261970004605246 } } }, "UnityEnvironment.step": { "total": 8561.87638640275, "count": 470579, "is_parallel": true, "self": 467.88636530699114, "children": { "UnityEnvironment._generate_step_input": { "total": 491.09489839930757, "count": 470579, "is_parallel": true, "self": 491.09489839930757 }, "communicator.exchange": { "total": 5946.11686529972, "count": 470579, "is_parallel": true, "self": 5946.11686529972 }, "steps_from_proto": { "total": 1656.7782573967306, "count": 941158, "is_parallel": true, "self": 328.72728599630864, "children": { "_process_rank_one_or_two_observation": { "total": 1328.050971400422, "count": 3764632, "is_parallel": true, "self": 1328.050971400422 } } } } } } } } } } }, "trainer_advance": { "total": 48658.6792410987, "count": 470579, "self": 115.30534269938653, "children": { "process_trajectory": { "total": 3572.8538944993197, "count": 470579, "self": 3569.30090909932, "children": { "RLTrainer._checkpoint": { "total": 3.5529853999996703, "count": 14, "self": 3.5529853999996703 } } }, "_update_policy": { "total": 44970.52000389999, "count": 337, "self": 2890.5338558003423, "children": { "TorchPOCAOptimizer.update": { "total": 42079.98614809965, "count": 16850, "self": 42079.98614809965 } } } } } } }, "trainer_threads": { "total": 1.300009898841381e-06, "count": 1, "self": 1.300009898841381e-06 }, "TrainerController._save_models": { "total": 0.27318540000123903, "count": 1, "self": 0.02383410000766162, "children": { "RLTrainer._checkpoint": { "total": 0.2493512999935774, "count": 1, "self": 0.2493512999935774 } } } } } } }