{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.4800455570220947, "min": 1.3649946451187134, "max": 3.295717716217041, "count": 5000 }, "SoccerTwos.Policy.Entropy.sum": { "value": 27090.75390625, "min": 22014.419921875, "max": 133619.40625, "count": 5000 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 73.94029850746269, "min": 41.17796610169491, "max": 999.0, "count": 5000 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19816.0, "min": 4160.0, "max": 32540.0, "count": 5000 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1746.5407722063626, "min": 1193.2592243039162, "max": 1789.724035282539, "count": 4991 }, "SoccerTwos.Self-play.ELO.sum": { "value": 234036.4634756526, "min": 2386.6032846542585, "max": 381095.2237354428, "count": 4991 }, "SoccerTwos.Step.mean": { "value": 49999978.0, "min": 9552.0, "max": 49999978.0, "count": 5000 }, "SoccerTwos.Step.sum": { "value": 49999978.0, "min": 9552.0, "max": 49999978.0, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.017178144305944443, "min": -0.1585976630449295, "max": 0.1933819055557251, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -2.2846932411193848, "min": -26.327213287353516, "max": 28.09320068359375, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.016565224155783653, "min": -0.1575256586074829, "max": 0.19438543915748596, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -2.2031748294830322, "min": -26.149259567260742, "max": 29.14250946044922, "count": 5000 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 5000 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": 0.06752180694637441, "min": -0.8571428571428571, "max": 0.6242222200941157, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 8.980400323867798, "min": -57.54120010137558, "max": 65.30160021781921, "count": 5000 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.06752180694637441, "min": -0.8571428571428571, "max": 0.6242222200941157, "count": 5000 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 8.980400323867798, "min": -57.54120010137558, "max": 65.30160021781921, "count": 5000 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 5000 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 5000 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.015497556823538617, "min": 0.01058001607695284, "max": 0.026931844577969363, "count": 2423 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.015497556823538617, "min": 0.01058001607695284, "max": 0.026931844577969363, "count": 2423 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.07395109509428342, "min": 0.0007833544218253034, "max": 0.12187003021438916, "count": 2423 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.07395109509428342, "min": 0.0007833544218253034, "max": 0.12187003021438916, "count": 2423 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.07477411528428396, "min": 0.0007905050030482622, "max": 0.12360076655944188, "count": 2423 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.07477411528428396, "min": 0.0007905050030482622, "max": 0.12360076655944188, "count": 2423 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 2423 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 2423 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.19999999999999996, "max": 0.20000000000000007, "count": 2423 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.19999999999999996, "max": 0.20000000000000007, "count": 2423 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 2423 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 2423 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1721162443", "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\\sifat\\miniconda3\\envs\\rl_unity\\Scripts\\mlagents-learn C:/Users/sifat/ml-agents/config/poca/SoccerTwos.yaml --env=C:/Users/sifat/ml-agents/training-envs-executables/SoccerTwos/SoccerTwos.exe --run-id=SoccerTwos_v1 --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.3.1+cpu", "numpy_version": "1.23.5", "end_time_seconds": "1721285505" }, "total": 123062.0297479, "count": 1, "self": 0.66863860002195, "children": { "run_training.setup": { "total": 0.09488839999903576, "count": 1, "self": 0.09488839999903576 }, "TrainerController.start_learning": { "total": 123061.26622089998, "count": 1, "self": 77.26314061989251, "children": { "TrainerController._reset_env": { "total": 9.97571519997291, "count": 200, "self": 9.97571519997291 }, "TrainerController.advance": { "total": 122973.87472338011, "count": 3422081, "self": 68.49092210415984, "children": { "env_step": { "total": 54550.430666674336, "count": 3422081, "self": 43119.715732391414, "children": { "SubprocessEnvManager._take_step": { "total": 11380.795904095721, "count": 3422081, "self": 388.16760619624256, "children": { "TorchPolicy.evaluate": { "total": 10992.628297899479, "count": 6275562, "self": 10992.628297899479 } } }, "workers": { "total": 49.91903018719677, "count": 3422081, "self": 0.0, "children": { "worker_root": { "total": 122960.3320597082, "count": 3422081, "is_parallel": true, "self": 88842.17441241772, "children": { "steps_from_proto": { "total": 0.3492209999494662, "count": 400, "is_parallel": true, "self": 0.062222600434324704, "children": { "_process_rank_one_or_two_observation": { "total": 0.2869983995151415, "count": 1600, "is_parallel": true, "self": 0.2869983995151415 } } }, "UnityEnvironment.step": { "total": 34117.80842629053, "count": 3422081, "is_parallel": true, "self": 1659.7009556700832, "children": { "UnityEnvironment._generate_step_input": { "total": 1452.251939396505, "count": 3422081, "is_parallel": true, "self": 1452.251939396505 }, "communicator.exchange": { "total": 25477.319964705475, "count": 3422081, "is_parallel": true, "self": 25477.319964705475 }, "steps_from_proto": { "total": 5528.535566518469, "count": 6844162, "is_parallel": true, "self": 981.9676343791398, "children": { "_process_rank_one_or_two_observation": { "total": 4546.567932139329, "count": 27376648, "is_parallel": true, "self": 4546.567932139329 } } } } } } } } } } }, "trainer_advance": { "total": 68354.95313460162, "count": 3422081, "self": 662.4093480269366, "children": { "process_trajectory": { "total": 12581.152080575554, "count": 3422081, "self": 12568.98895087554, "children": { "RLTrainer._checkpoint": { "total": 12.163129700013087, "count": 100, "self": 12.163129700013087 } } }, "_update_policy": { "total": 55111.39170599913, "count": 2423, "self": 8546.09835039841, "children": { "TorchPOCAOptimizer.update": { "total": 46565.29335560072, "count": 72702, "self": 46565.29335560072 } } } } } } }, "trainer_threads": { "total": 8.00006091594696e-07, "count": 1, "self": 8.00006091594696e-07 }, "TrainerController._save_models": { "total": 0.15264089999254793, "count": 1, "self": 0.0371175000036601, "children": { "RLTrainer._checkpoint": { "total": 0.11552339998888783, "count": 1, "self": 0.11552339998888783 } } } } } } }