{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 3.205953598022461, "min": 3.1314074993133545, "max": 3.295724391937256, "count": 500 }, "SoccerTwos.Policy.Entropy.sum": { "value": 53962.609375, "min": 14365.044921875, "max": 133422.21875, "count": 500 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 710.5, "min": 417.0833333333333, "max": 999.0, "count": 500 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 17052.0, "min": 14820.0, "max": 26112.0, "count": 500 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1184.897121839943, "min": 1184.897121839943, "max": 1209.7504509877854, "count": 405 }, "SoccerTwos.Self-play.ELO.sum": { "value": 7109.382731039659, "min": 2372.098120011844, "max": 21708.334058858858, "count": 405 }, "SoccerTwos.Step.mean": { "value": 4999790.0, "min": 9072.0, "max": 4999790.0, "count": 500 }, "SoccerTwos.Step.sum": { "value": 4999790.0, "min": 9072.0, "max": 4999790.0, "count": 500 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.008271324448287487, "min": -0.02977818064391613, "max": 0.014759513549506664, "count": 500 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -0.1075272187590599, "min": -0.4168945252895355, "max": 0.1836538314819336, "count": 500 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.011229801923036575, "min": -0.02888304367661476, "max": 0.014632614329457283, "count": 500 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -0.14598742127418518, "min": -0.43324771523475647, "max": 0.18205992877483368, "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": -0.14307692417731652, "min": -0.6030769210595351, "max": 0.38701175942140464, "count": 500 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -1.8600000143051147, "min": -8.63479995727539, "max": 6.579199910163879, "count": 500 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.14307692417731652, "min": -0.6030769210595351, "max": 0.38701175942140464, "count": 500 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -1.8600000143051147, "min": -8.63479995727539, "max": 6.579199910163879, "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": 0.019428684155961187, "min": 0.00999447045414854, "max": 0.023810121327793848, "count": 233 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.019428684155961187, "min": 0.00999447045414854, "max": 0.023810121327793848, "count": 233 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.0045237826416268945, "min": 6.480804221572119e-07, "max": 0.007653752823049823, "count": 233 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.0045237826416268945, "min": 6.480804221572119e-07, "max": 0.007653752823049823, "count": 233 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.004531491803936661, "min": 7.146187120573207e-07, "max": 0.007737341243773699, "count": 233 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.004531491803936661, "min": 7.146187120573207e-07, "max": 0.007737341243773699, "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": "1716537583", "python_version": "3.10.12 (main, Jul 5 2023, 15:02:25) [Clang 14.0.6 ]", "command_line_arguments": "/Users/johnnyf/anaconda3/envs/rl/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=/Users/johnnyf/Documents/Learning/Data Science (HuggingFace)/2vs2/ml-agents/training-envs-executables/SoccerTwos/SoccerTwos.app --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", "numpy_version": "1.23.5", "end_time_seconds": "1716553215" }, "total": 15632.168753417005, "count": 1, "self": 0.24280958400049713, "children": { "run_training.setup": { "total": 0.013176958003896289, "count": 1, "self": 0.013176958003896289 }, "TrainerController.start_learning": { "total": 15631.912766875, "count": 1, "self": 2.3461087064206367, "children": { "TrainerController._reset_env": { "total": 4.399072625979898, "count": 25, "self": 4.399072625979898 }, "TrainerController.advance": { "total": 15625.069361126603, "count": 324988, "self": 2.1885476429160917, "children": { "env_step": { "total": 12803.093972983464, "count": 324988, "self": 12409.598438564135, "children": { "SubprocessEnvManager._take_step": { "total": 391.75373044495063, "count": 324988, "self": 12.512030485027935, "children": { "TorchPolicy.evaluate": { "total": 379.2416999599227, "count": 645206, "self": 379.2416999599227 } } }, "workers": { "total": 1.741803974378854, "count": 324988, "self": 0.0, "children": { "worker_root": { "total": 15625.0689599537, "count": 324988, "is_parallel": true, "self": 3587.249148508985, "children": { "steps_from_proto": { "total": 0.033551461005117744, "count": 50, "is_parallel": true, "self": 0.00454570104193408, "children": { "_process_rank_one_or_two_observation": { "total": 0.029005759963183664, "count": 200, "is_parallel": true, "self": 0.029005759963183664 } } }, "UnityEnvironment.step": { "total": 12037.78625998371, "count": 324988, "is_parallel": true, "self": 31.50657585017325, "children": { "UnityEnvironment._generate_step_input": { "total": 197.16775916561892, "count": 324988, "is_parallel": true, "self": 197.16775916561892 }, "communicator.exchange": { "total": 11399.821300428768, "count": 324988, "is_parallel": true, "self": 11399.821300428768 }, "steps_from_proto": { "total": 409.2906245391496, "count": 649976, "is_parallel": true, "self": 45.989281766465865, "children": { "_process_rank_one_or_two_observation": { "total": 363.3013427726837, "count": 2599904, "is_parallel": true, "self": 363.3013427726837 } } } } } } } } } } }, "trainer_advance": { "total": 2819.7868405002228, "count": 324988, "self": 26.30770409476827, "children": { "process_trajectory": { "total": 419.61333831751836, "count": 324988, "self": 418.59344798352686, "children": { "RLTrainer._checkpoint": { "total": 1.0198903339914978, "count": 10, "self": 1.0198903339914978 } } }, "_update_policy": { "total": 2373.865798087936, "count": 233, "self": 276.29951186620747, "children": { "TorchPOCAOptimizer.update": { "total": 2097.5662862217287, "count": 6990, "self": 2097.5662862217287 } } } } } } }, "trainer_threads": { "total": 4.5797787606716156e-07, "count": 1, "self": 4.5797787606716156e-07 }, "TrainerController._save_models": { "total": 0.09822395801893435, "count": 1, "self": 0.0010266670142300427, "children": { "RLTrainer._checkpoint": { "total": 0.09719729100470431, "count": 1, "self": 0.09719729100470431 } } } } } } }