{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 3.1335902214050293, "min": 3.044464588165283, "max": 3.2957401275634766, "count": 500 }, "SoccerTwos.Policy.Entropy.sum": { "value": 66582.5234375, "min": 19254.259765625, "max": 145914.34375, "count": 500 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 785.1428571428571, "min": 453.9166666666667, "max": 999.0, "count": 500 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 21984.0, "min": 15700.0, "max": 26792.0, "count": 500 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1201.1012973202883, "min": 1198.0085529528465, "max": 1214.780299156555, "count": 366 }, "SoccerTwos.Self-play.ELO.sum": { "value": 4804.405189281153, "min": 2397.1239012245687, "max": 21752.755057211583, "count": 366 }, "SoccerTwos.Step.mean": { "value": 4999764.0, "min": 9416.0, "max": 4999764.0, "count": 500 }, "SoccerTwos.Step.sum": { "value": 4999764.0, "min": 9416.0, "max": 4999764.0, "count": 500 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.013091187924146652, "min": -0.03451749309897423, "max": 0.015445241704583168, "count": 500 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -0.17018544673919678, "min": -0.5023853778839111, "max": 0.21623338758945465, "count": 500 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.013134438544511795, "min": -0.0353570431470871, "max": 0.02151164598762989, "count": 500 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -0.17074769735336304, "min": -0.5068726539611816, "max": 0.30116304755210876, "count": 500 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 500 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 500 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.024753843935636375, "min": -0.5993176453253802, "max": 0.3671466668446859, "count": 500 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -0.32179997116327286, "min": -10.188399970531464, "max": 6.71199993789196, "count": 500 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.024753843935636375, "min": -0.5993176453253802, "max": 0.3671466668446859, "count": 500 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -0.32179997116327286, "min": -10.188399970531464, "max": 6.71199993789196, "count": 500 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 500 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 500 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.01658890542651837, "min": 0.011293572919385042, "max": 0.02451348736649379, "count": 233 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.01658890542651837, "min": 0.011293572919385042, "max": 0.02451348736649379, "count": 233 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.003009323418761293, "min": 1.1716557655934897e-07, "max": 0.008516330225393175, "count": 233 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.003009323418761293, "min": 1.1716557655934897e-07, "max": 0.008516330225393175, "count": 233 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.003013923985417932, "min": 1.2282477494333458e-07, "max": 0.008516281036039193, "count": 233 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.003013923985417932, "min": 1.2282477494333458e-07, "max": 0.008516281036039193, "count": 233 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 233 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 233 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 233 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 233 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 233 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 233 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1681198458", "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": "1.8.0+cu111", "numpy_version": "1.21.2", "end_time_seconds": "1681206323" }, "total": 7865.0801193, "count": 1, "self": 0.33510479999858944, "children": { "run_training.setup": { "total": 0.10369950000000028, "count": 1, "self": 0.10369950000000028 }, "TrainerController.start_learning": { "total": 7864.641315000001, "count": 1, "self": 6.463022699677822, "children": { "TrainerController._reset_env": { "total": 5.6894242000000474, "count": 25, "self": 5.6894242000000474 }, "TrainerController.advance": { "total": 7852.289783500322, "count": 325196, "self": 7.333789100373906, "children": { "env_step": { "total": 6084.473937999983, "count": 325196, "self": 3911.8350852999065, "children": { "SubprocessEnvManager._take_step": { "total": 2168.2869328001198, "count": 325196, "self": 44.988823900178886, "children": { "TorchPolicy.evaluate": { "total": 2123.298108899941, "count": 645612, "self": 2123.298108899941 } } }, "workers": { "total": 4.351919899956753, "count": 325196, "self": 0.0, "children": { "worker_root": { "total": 7852.238587099559, "count": 325196, "is_parallel": true, "self": 4735.600605399779, "children": { "steps_from_proto": { "total": 0.03662960000368365, "count": 50, "is_parallel": true, "self": 0.008072300008106215, "children": { "_process_rank_one_or_two_observation": { "total": 0.028557299995577434, "count": 200, "is_parallel": true, "self": 0.028557299995577434 } } }, "UnityEnvironment.step": { "total": 3116.601352099776, "count": 325196, "is_parallel": true, "self": 162.09485569977733, "children": { "UnityEnvironment._generate_step_input": { "total": 127.42359859988306, "count": 325196, "is_parallel": true, "self": 127.42359859988306 }, "communicator.exchange": { "total": 2331.550481499904, "count": 325196, "is_parallel": true, "self": 2331.550481499904 }, "steps_from_proto": { "total": 495.53241630021137, "count": 650392, "is_parallel": true, "self": 105.98454580025566, "children": { "_process_rank_one_or_two_observation": { "total": 389.5478704999557, "count": 2601568, "is_parallel": true, "self": 389.5478704999557 } } } } } } } } } } }, "trainer_advance": { "total": 1760.4820563999658, "count": 325196, "self": 48.19211039984657, "children": { "process_trajectory": { "total": 451.7246628001132, "count": 325196, "self": 449.66450260011135, "children": { "RLTrainer._checkpoint": { "total": 2.06016020000186, "count": 10, "self": 2.06016020000186 } } }, "_update_policy": { "total": 1260.565283200006, "count": 233, "self": 745.373231400002, "children": { "TorchPOCAOptimizer.update": { "total": 515.1920518000039, "count": 6990, "self": 515.1920518000039 } } } } } } }, "trainer_threads": { "total": 7.000007826718502e-07, "count": 1, "self": 7.000007826718502e-07 }, "TrainerController._save_models": { "total": 0.1990839000000051, "count": 1, "self": 0.003749499999685213, "children": { "RLTrainer._checkpoint": { "total": 0.19533440000031987, "count": 1, "self": 0.19533440000031987 } } } } } } }