{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.991182565689087, "min": 1.991182565689087, "max": 2.3107833862304688, "count": 20 }, "SoccerTwos.Policy.Entropy.sum": { "value": 198863.390625, "min": 198863.390625, "max": 232557.25, "count": 20 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 54.242290748898675, "min": 47.715953307392994, "max": 59.204819277108435, "count": 20 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 98504.0, "min": 97352.0, "max": 98564.0, "count": 20 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1596.8856160680812, "min": 1520.4333709905238, "max": 1596.8856160680812, "count": 20 }, "SoccerTwos.Self-play.ELO.sum": { "value": 1449972.1393898176, "min": 1261959.6979221348, "max": 1597547.9131219038, "count": 20 }, "SoccerTwos.Step.mean": { "value": 5999858.0, "min": 5049956.0, "max": 5999858.0, "count": 20 }, "SoccerTwos.Step.sum": { "value": 5999858.0, "min": 5049956.0, "max": 5999858.0, "count": 20 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": 0.01571565866470337, "min": -0.03754736855626106, "max": 0.0836557149887085, "count": 20 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": 14.269817352294922, "min": -31.164316177368164, "max": 80.19994354248047, "count": 20 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": 0.014159336686134338, "min": -0.03675474971532822, "max": 0.08358553797006607, "count": 20 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": 12.856678009033203, "min": -30.50644302368164, "max": 79.80325317382812, "count": 20 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 20 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 20 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.06581629976827143, "min": -0.07461106190375522, "max": 0.12742424346667863, "count": 20 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -59.761200189590454, "min": -67.44839996099472, "max": 117.74000096321106, "count": 20 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.06581629976827143, "min": -0.07461106190375522, "max": 0.12742424346667863, "count": 20 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -59.761200189590454, "min": -67.44839996099472, "max": 117.74000096321106, "count": 20 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.017259779567151176, "min": 0.013903003576948927, "max": 0.018675298746287202, "count": 20 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.03451955913430235, "min": 0.027806007153897853, "max": 0.05332428064575652, "count": 20 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.10991844969491163, "min": 0.09613035536474653, "max": 0.11699956779678664, "count": 20 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.21983689938982326, "min": 0.19462583710749942, "max": 0.33388328850269317, "count": 20 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.11183060631155968, "min": 0.09769865911867882, "max": 0.11947158152858417, "count": 20 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.22366121262311936, "min": 0.19866952300071716, "max": 0.33829459423820174, "count": 20 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 20 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0006, "min": 0.0006, "max": 0.0009, "count": 20 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 20 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.40000000000000013, "min": 0.40000000000000013, "max": 0.6000000000000002, "count": 20 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 20 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.010000000000000002, "min": 0.010000000000000002, "max": 0.015000000000000003, "count": 20 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 20 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 20 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1688705682", "python_version": "3.9.13 (tags/v3.9.13:6de2ca5, May 17 2022, 16:36:42) [MSC v.1929 64 bit (AMD64)]", "command_line_arguments": "C:\\cygwin64\\home\\zmusc\\git_repos\\hf-deep-rl-course-unit7handson\\venv\\Scripts\\mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos/SoccerTwos.exe --run-id=SoccerTwos --no-graphics --resume", "mlagents_version": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.9.0+cu111", "numpy_version": "1.21.2", "end_time_seconds": "1688707031" }, "total": 1350.0074677, "count": 1, "self": 0.21273450000012417, "children": { "run_training.setup": { "total": 0.12336409999999987, "count": 1, "self": 0.12336409999999987 }, "TrainerController.start_learning": { "total": 1349.6713691, "count": 1, "self": 1.165658700003405, "children": { "TrainerController._reset_env": { "total": 2.8202560000002506, "count": 7, "self": 2.8202560000002506 }, "TrainerController.advance": { "total": 1345.5291634999962, "count": 70174, "self": 1.0655464999508695, "children": { "env_step": { "total": 951.0618612000178, "count": 70174, "self": 590.5109055000164, "children": { "SubprocessEnvManager._take_step": { "total": 359.8672633000093, "count": 70174, "self": 5.474472699996113, "children": { "TorchPolicy.evaluate": { "total": 354.3927906000132, "count": 125362, "self": 354.3927906000132 } } }, "workers": { "total": 0.6836923999920055, "count": 70174, "self": 0.0, "children": { "worker_root": { "total": 1346.2262785999642, "count": 70174, "is_parallel": true, "self": 870.1020653999858, "children": { "steps_from_proto": { "total": 0.007733100000117288, "count": 12, "is_parallel": true, "self": 0.0017047000002894386, "children": { "_process_rank_one_or_two_observation": { "total": 0.006028399999827849, "count": 48, "is_parallel": true, "self": 0.006028399999827849 } } }, "UnityEnvironment.step": { "total": 476.11648009997833, "count": 70174, "is_parallel": true, "self": 27.08991029995542, "children": { "UnityEnvironment._generate_step_input": { "total": 19.331992400010115, "count": 70174, "is_parallel": true, "self": 19.331992400010115 }, "communicator.exchange": { "total": 350.2684715000071, "count": 70174, "is_parallel": true, "self": 350.2684715000071 }, "steps_from_proto": { "total": 79.42610590000574, "count": 140348, "is_parallel": true, "self": 17.727934800009173, "children": { "_process_rank_one_or_two_observation": { "total": 61.698171099996564, "count": 561392, "is_parallel": true, "self": 61.698171099996564 } } } } } } } } } } }, "trainer_advance": { "total": 393.40175580002756, "count": 70174, "self": 7.691731500006881, "children": { "process_trajectory": { "total": 213.01986200002028, "count": 70174, "self": 212.71671580002027, "children": { "RLTrainer._checkpoint": { "total": 0.3031462000000147, "count": 2, "self": 0.3031462000000147 } } }, "_update_policy": { "total": 172.6901623000004, "count": 48, "self": 110.52477350000055, "children": { "TorchPOCAOptimizer.update": { "total": 62.165388799999846, "count": 1440, "self": 62.165388799999846 } } } } } } }, "trainer_threads": { "total": 6.000000212225132e-07, "count": 1, "self": 6.000000212225132e-07 }, "TrainerController._save_models": { "total": 0.156290300000137, "count": 1, "self": 0.02723340000011376, "children": { "RLTrainer._checkpoint": { "total": 0.12905690000002323, "count": 1, "self": 0.12905690000002323 } } } } } } }