{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 2.0461297035217285, "min": 2.0161590576171875, "max": 3.2957279682159424, "count": 519 }, "SoccerTwos.Policy.Entropy.sum": { "value": 43017.83203125, "min": 32434.61328125, "max": 106503.078125, "count": 519 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 64.78947368421052, "min": 39.29032258064516, "max": 999.0, "count": 519 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19696.0, "min": 7992.0, "max": 28480.0, "count": 519 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1600.2931324517665, "min": 1191.2399676831446, "max": 1609.1342377675796, "count": 511 }, "SoccerTwos.Self-play.ELO.sum": { "value": 243244.5561326685, "min": 2382.974437598412, "max": 365896.1831838081, "count": 511 }, "SoccerTwos.Step.mean": { "value": 5189960.0, "min": 9180.0, "max": 5189960.0, "count": 519 }, "SoccerTwos.Step.sum": { "value": 5189960.0, "min": 9180.0, "max": 5189960.0, "count": 519 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.003742633620277047, "min": -0.1260470300912857, "max": 0.13582776486873627, "count": 519 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -0.5651376843452454, "min": -22.490745544433594, "max": 27.301382064819336, "count": 519 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.0027731729205697775, "min": -0.127252459526062, "max": 0.14110778272151947, "count": 519 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -0.4187490940093994, "min": -21.518491744995117, "max": 28.36266326904297, "count": 519 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 519 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 519 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.061898011640207654, "min": -0.5380363633686845, "max": 0.5209363617680289, "count": 519 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -9.346599757671356, "min": -59.39400005340576, "max": 54.168399930000305, "count": 519 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.061898011640207654, "min": -0.5380363633686845, "max": 0.5209363617680289, "count": 519 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -9.346599757671356, "min": -59.39400005340576, "max": 54.168399930000305, "count": 519 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 519 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 519 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.017423143272753804, "min": 0.011799349438903543, "max": 0.02284480881644413, "count": 250 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.017423143272753804, "min": 0.011799349438903543, "max": 0.02284480881644413, "count": 250 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.08871468206246694, "min": 0.0005195737214914212, "max": 0.11782725875576337, "count": 250 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.08871468206246694, "min": 0.0005195737214914212, "max": 0.11782725875576337, "count": 250 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.09064463103810946, "min": 0.0005199280873057433, "max": 0.12027590995033582, "count": 250 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.09064463103810946, "min": 0.0005199280873057433, "max": 0.12027590995033582, "count": 250 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 250 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 250 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000004, "max": 0.20000000000000007, "count": 250 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000004, "max": 0.20000000000000007, "count": 250 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 250 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 250 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1717873602", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos.x86_64 --run-id=SoccerTwos --no-graphics --force", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.3.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1717905430" }, "total": 31827.071581471, "count": 1, "self": 0.5007271999966179, "children": { "run_training.setup": { "total": 0.06706941999999572, "count": 1, "self": 0.06706941999999572 }, "TrainerController.start_learning": { "total": 31826.503784851, "count": 1, "self": 13.475835468943842, "children": { "TrainerController._reset_env": { "total": 5.630503202995158, "count": 26, "self": 5.630503202995158 }, "TrainerController.advance": { "total": 31806.67343314006, "count": 354262, "self": 15.559166799732338, "children": { "env_step": { "total": 12255.390479661062, "count": 354262, "self": 9794.063875354896, "children": { "SubprocessEnvManager._take_step": { "total": 2452.5409078781486, "count": 354262, "self": 89.23789903526131, "children": { "TorchPolicy.evaluate": { "total": 2363.3030088428873, "count": 654598, "self": 2363.3030088428873 } } }, "workers": { "total": 8.785696428019094, "count": 354261, "self": 0.0, "children": { "worker_root": { "total": 31782.312993057487, "count": 354261, "is_parallel": true, "self": 23736.25620312977, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.006967739000003803, "count": 2, "is_parallel": true, "self": 0.004147210000098767, "children": { "_process_rank_one_or_two_observation": { "total": 0.0028205289999050365, "count": 8, "is_parallel": true, "self": 0.0028205289999050365 } } }, "UnityEnvironment.step": { "total": 0.048398853999970015, "count": 1, "is_parallel": true, "self": 0.00148812999987058, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0009771180000370805, "count": 1, "is_parallel": true, "self": 0.0009771180000370805 }, "communicator.exchange": { "total": 0.0417054790000293, "count": 1, "is_parallel": true, "self": 0.0417054790000293 }, "steps_from_proto": { "total": 0.004228127000033055, "count": 2, "is_parallel": true, "self": 0.0007427840000673314, "children": { "_process_rank_one_or_two_observation": { "total": 0.0034853429999657237, "count": 8, "is_parallel": true, "self": 0.0034853429999657237 } } } } } } }, "UnityEnvironment.step": { "total": 8045.987775509704, "count": 354260, "is_parallel": true, "self": 495.588772516212, "children": { "UnityEnvironment._generate_step_input": { "total": 318.45224689281997, "count": 354260, "is_parallel": true, "self": 318.45224689281997 }, "communicator.exchange": { "total": 5740.135135407552, "count": 354260, "is_parallel": true, "self": 5740.135135407552 }, "steps_from_proto": { "total": 1491.8116206931195, "count": 708520, "is_parallel": true, "self": 267.13504568602707, "children": { "_process_rank_one_or_two_observation": { "total": 1224.6765750070924, "count": 2834080, "is_parallel": true, "self": 1224.6765750070924 } } } } }, "steps_from_proto": { "total": 0.06901441801164765, "count": 50, "is_parallel": true, "self": 0.014484724977819496, "children": { "_process_rank_one_or_two_observation": { "total": 0.05452969303382815, "count": 200, "is_parallel": true, "self": 0.05452969303382815 } } } } } } } } }, "trainer_advance": { "total": 19535.723786679264, "count": 354261, "self": 104.75847420717764, "children": { "process_trajectory": { "total": 3085.4856409021254, "count": 354261, "self": 3082.5308854471264, "children": { "RLTrainer._checkpoint": { "total": 2.954755454999031, "count": 10, "self": 2.954755454999031 } } }, "_update_policy": { "total": 16345.47967156996, "count": 250, "self": 1121.2722514048983, "children": { "TorchPOCAOptimizer.update": { "total": 15224.207420165061, "count": 7509, "self": 15224.207420165061 } } } } } } }, "trainer_threads": { "total": 2.2620006348006427e-06, "count": 1, "self": 2.2620006348006427e-06 }, "TrainerController._save_models": { "total": 0.7240107770012401, "count": 1, "self": 0.012484205002692761, "children": { "RLTrainer._checkpoint": { "total": 0.7115265719985473, "count": 1, "self": 0.7115265719985473 } } } } } } }