{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.8433421850204468, "min": 1.7970082759857178, "max": 3.2957563400268555, "count": 500 }, "SoccerTwos.Policy.Entropy.sum": { "value": 37043.8046875, "min": 24494.115234375, "max": 108905.609375, "count": 500 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 73.58208955223881, "min": 38.976377952755904, "max": 999.0, "count": 500 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19720.0, "min": 16320.0, "max": 23672.0, "count": 500 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1623.6619002740933, "min": 1197.3314385033887, "max": 1635.9330874933617, "count": 498 }, "SoccerTwos.Self-play.ELO.sum": { "value": 217570.6946367285, "min": 2401.644872894947, "max": 401194.8356753671, "count": 498 }, "SoccerTwos.Step.mean": { "value": 4999993.0, "min": 9576.0, "max": 4999993.0, "count": 500 }, "SoccerTwos.Step.sum": { "value": 4999993.0, "min": 9576.0, "max": 4999993.0, "count": 500 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": 0.017407242208719254, "min": -0.09307114034891129, "max": 0.16990172863006592, "count": 500 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": 2.3325705528259277, "min": -16.86497688293457, "max": 32.003135681152344, "count": 500 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": 0.015660123899579048, "min": -0.09834237396717072, "max": 0.1734757423400879, "count": 500 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": 2.098456621170044, "min": -18.586708068847656, "max": 32.38905715942383, "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": -0.004726866287971611, "min": -0.7470117667142082, "max": 0.6358083337545395, "count": 500 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -0.6334000825881958, "min": -40.37979996204376, "max": 55.69720005989075, "count": 500 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.004726866287971611, "min": -0.7470117667142082, "max": 0.6358083337545395, "count": 500 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -0.6334000825881958, "min": -40.37979996204376, "max": 55.69720005989075, "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": 0.014727468194905668, "min": 0.0104228329641046, "max": 0.022719084483105688, "count": 241 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.014727468194905668, "min": 0.0104228329641046, "max": 0.022719084483105688, "count": 241 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.08477060049772263, "min": 0.0015971816416519384, "max": 0.12459605385859808, "count": 241 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.08477060049772263, "min": 0.0015971816416519384, "max": 0.12459605385859808, "count": 241 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.08569952224691708, "min": 0.0016171264597990862, "max": 0.1282633235057195, "count": 241 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.08569952224691708, "min": 0.0016171264597990862, "max": 0.1282633235057195, "count": 241 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 241 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 241 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 241 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 241 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 241 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 241 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1709620103", "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\\krvig\\miniconda3\\envs\\rl\\Scripts\\mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.exe --run-id=SoccerTwos --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.2.1+cpu", "numpy_version": "1.23.5", "end_time_seconds": "1709637683" }, "total": 17580.021488999948, "count": 1, "self": 1.8573480999330059, "children": { "run_training.setup": { "total": 0.09591729997191578, "count": 1, "self": 0.09591729997191578 }, "TrainerController.start_learning": { "total": 17578.068223600043, "count": 1, "self": 9.225787691189907, "children": { "TrainerController._reset_env": { "total": 17.3690497999778, "count": 25, "self": 17.3690497999778 }, "TrainerController.advance": { "total": 17551.351071608835, "count": 342407, "self": 8.523460018681362, "children": { "env_step": { "total": 5853.236419308814, "count": 342407, "self": 4543.120471705333, "children": { "SubprocessEnvManager._take_step": { "total": 1304.4824818982743, "count": 342407, "self": 45.518637108267285, "children": { "TorchPolicy.evaluate": { "total": 1258.963844790007, "count": 629008, "self": 1258.963844790007 } } }, "workers": { "total": 5.633465705206618, "count": 342407, "self": 0.0, "children": { "worker_root": { "total": 17548.919835784007, "count": 342407, "is_parallel": true, "self": 14030.47851277457, "children": { "steps_from_proto": { "total": 0.048653599922545254, "count": 50, "is_parallel": true, "self": 0.00951929995790124, "children": { "_process_rank_one_or_two_observation": { "total": 0.039134299964644015, "count": 200, "is_parallel": true, "self": 0.039134299964644015 } } }, "UnityEnvironment.step": { "total": 3518.3926694095135, "count": 342407, "is_parallel": true, "self": 191.90037638531066, "children": { "UnityEnvironment._generate_step_input": { "total": 170.4149898774922, "count": 342407, "is_parallel": true, "self": 170.4149898774922 }, "communicator.exchange": { "total": 2516.3398052871926, "count": 342407, "is_parallel": true, "self": 2516.3398052871926 }, "steps_from_proto": { "total": 639.737497859518, "count": 684814, "is_parallel": true, "self": 131.73322949022986, "children": { "_process_rank_one_or_two_observation": { "total": 508.0042683692882, "count": 2739256, "is_parallel": true, "self": 508.0042683692882 } } } } } } } } } } }, "trainer_advance": { "total": 11689.59119228134, "count": 342407, "self": 76.03407736099325, "children": { "process_trajectory": { "total": 1820.5249719200656, "count": 342407, "self": 1819.2536083199084, "children": { "RLTrainer._checkpoint": { "total": 1.2713636001572013, "count": 10, "self": 1.2713636001572013 } } }, "_update_policy": { "total": 9793.03214300028, "count": 241, "self": 708.9029265014688, "children": { "TorchPOCAOptimizer.update": { "total": 9084.129216498812, "count": 7230, "self": 9084.129216498812 } } } } } } }, "trainer_threads": { "total": 1.00000761449337e-06, "count": 1, "self": 1.00000761449337e-06 }, "TrainerController._save_models": { "total": 0.1223135000327602, "count": 1, "self": 0.00904690008610487, "children": { "RLTrainer._checkpoint": { "total": 0.11326659994665533, "count": 1, "self": 0.11326659994665533 } } } } } } }