{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 3.0953874588012695, "min": 3.0953874588012695, "max": 3.2946317195892334, "count": 78 }, "SoccerTwos.Policy.Entropy.sum": { "value": 17928.484375, "min": 3954.2001953125, "max": 105428.21875, "count": 78 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 966.5, "min": 219.88888888888889, "max": 999.0, "count": 78 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 7732.0, "min": 2536.0, "max": 24632.0, "count": 78 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1202.5900716306517, "min": 1199.9202472092547, "max": 1206.5010921371231, "count": 54 }, "SoccerTwos.Self-play.ELO.sum": { "value": 2405.1801432613033, "min": 2403.498433353844, "max": 12057.767178482298, "count": 54 }, "SoccerTwos.Step.mean": { "value": 399123.0, "min": 4332.0, "max": 399123.0, "count": 80 }, "SoccerTwos.Step.sum": { "value": 399123.0, "min": 4332.0, "max": 399123.0, "count": 80 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.0028270359616726637, "min": -0.015790298581123352, "max": 0.009247126057744026, "count": 80 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -0.014135180041193962, "min": -0.12632238864898682, "max": 0.04623563215136528, "count": 80 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.0028270361945033073, "min": -0.015790289267897606, "max": 0.009247127920389175, "count": 80 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -0.014135180972516537, "min": -0.12632231414318085, "max": 0.04623563960194588, "count": 80 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 80 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 80 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": 0.012919999659061432, "min": -0.5, "max": 0.5408363721587441, "count": 80 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 0.06459999829530716, "min": -5.0848000049591064, "max": 5.949200093746185, "count": 80 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.012919999659061432, "min": -0.5, "max": 0.5408363721587441, "count": 80 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 0.06459999829530716, "min": -5.0848000049591064, "max": 5.949200093746185, "count": 80 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.03599075341597199, "min": 0.02652264821117569, "max": 0.03958484005124774, "count": 78 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.03599075341597199, "min": 0.02737326630934452, "max": 0.1006289279997353, "count": 78 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.002975616512121633, "min": 4.912644244387317e-12, "max": 0.0040068723130389115, "count": 78 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.002975616512121633, "min": 9.825288488774635e-12, "max": 0.008013744626077823, "count": 78 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.0029756165039725602, "min": 4.912676342611613e-12, "max": 0.004006872307218146, "count": 78 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.0029756165039725602, "min": 9.825352685223225e-12, "max": 0.008013744614436292, "count": 78 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.00030000000000000014, "count": 78 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0009, "count": 78 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.09999999999999998, "min": 0.09999999999999996, "max": 0.1, "count": 78 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.09999999999999998, "min": 0.09999999999999996, "max": 0.29999999999999993, "count": 78 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.0004000000000000001, "min": 0.00039999999999999996, "max": 0.0004000000000000002, "count": 78 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.0004000000000000001, "min": 0.00039999999999999996, "max": 0.0012000000000000001, "count": 78 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 80 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 80 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1699128120", "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\\darkd\\miniconda3\\envs\\rl\\Scripts\\mlagents-learn .\\config\\poca\\behaviors.yml --env=.\\training-envs-executable\\SoccerTwos\\SoccerTwos.exe --run-id=xovernightx --no-graphics --force", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.0.0+cpu", "numpy_version": "1.23.5", "end_time_seconds": "1699130648" }, "total": 2527.6832791999987, "count": 1, "self": 0.33226709999871673, "children": { "run_training.setup": { "total": 0.14834870000049705, "count": 1, "self": 0.14834870000049705 }, "TrainerController.start_learning": { "total": 2527.2026633999994, "count": 1, "self": 1.2376500002355897, "children": { "TrainerController._reset_env": { "total": 6.365150799974799, "count": 19, "self": 6.365150799974799 }, "TrainerController.advance": { "total": 2519.307256399792, "count": 33101, "self": 1.1794261996183195, "children": { "env_step": { "total": 934.8396340999607, "count": 33101, "self": 708.1390166005003, "children": { "SubprocessEnvManager._take_step": { "total": 225.90577660004783, "count": 33101, "self": 7.087370800196368, "children": { "TorchPolicy.evaluate": { "total": 218.81840579985146, "count": 65732, "self": 218.81840579985146 } } }, "workers": { "total": 0.7948408994125202, "count": 33101, "self": 0.0, "children": { "worker_root": { "total": 2520.518991699988, "count": 33101, "is_parallel": true, "self": 1967.1660637001332, "children": { "steps_from_proto": { "total": 0.04562999999325257, "count": 38, "is_parallel": true, "self": 0.010100100022100378, "children": { "_process_rank_one_or_two_observation": { "total": 0.03552989997115219, "count": 152, "is_parallel": true, "self": 0.03552989997115219 } } }, "UnityEnvironment.step": { "total": 553.3072979998615, "count": 33101, "is_parallel": true, "self": 27.095727399908355, "children": { "UnityEnvironment._generate_step_input": { "total": 25.477302699480788, "count": 33101, "is_parallel": true, "self": 25.477302699480788 }, "communicator.exchange": { "total": 406.09700419979345, "count": 33101, "is_parallel": true, "self": 406.09700419979345 }, "steps_from_proto": { "total": 94.63726370067889, "count": 66202, "is_parallel": true, "self": 20.000750102903112, "children": { "_process_rank_one_or_two_observation": { "total": 74.63651359777577, "count": 264808, "is_parallel": true, "self": 74.63651359777577 } } } } } } } } } } }, "trainer_advance": { "total": 1583.288196100213, "count": 33101, "self": 7.677287199570856, "children": { "process_trajectory": { "total": 88.717625300691, "count": 33101, "self": 88.717625300691 }, "_update_policy": { "total": 1486.8932835999512, "count": 122, "self": 292.86508180006786, "children": { "TorchPOCAOptimizer.update": { "total": 1194.0282017998834, "count": 7060, "self": 1194.0282017998834 } } } } } } }, "trainer_threads": { "total": 1.4999968698248267e-06, "count": 1, "self": 1.4999968698248267e-06 }, "TrainerController._save_models": { "total": 0.29260470000008354, "count": 1, "self": 0.010557099994912278, "children": { "RLTrainer._checkpoint": { "total": 0.28204760000517126, "count": 1, "self": 0.28204760000517126 } } } } } } }