{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.8603078126907349, "min": 1.8603078126907349, "max": 2.1334164142608643, "count": 209 }, "SoccerTwos.Policy.Entropy.sum": { "value": 38337.22265625, "min": 12103.240234375, "max": 46377.265625, "count": 209 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 50.65979381443299, "min": 37.25757575757576, "max": 67.65277777777777, "count": 209 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19656.0, "min": 4332.0, "max": 20220.0, "count": 209 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1508.4571102358263, "min": 1410.7677734512024, "max": 1508.4571102358263, "count": 209 }, "SoccerTwos.Self-play.ELO.sum": { "value": 292640.6793857503, "min": 80684.63604765123, "max": 389486.18281116325, "count": 209 }, "SoccerTwos.Step.mean": { "value": 5559968.0, "min": 3479968.0, "max": 5559968.0, "count": 209 }, "SoccerTwos.Step.sum": { "value": 5559968.0, "min": 3479968.0, "max": 5559968.0, "count": 209 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": 0.06590203195810318, "min": -0.10732022672891617, "max": 0.11532635241746902, "count": 209 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": 12.71909236907959, "min": -19.74692153930664, "max": 23.641902923583984, "count": 209 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": 0.07202169299125671, "min": -0.11327219754457474, "max": 0.11728597432374954, "count": 209 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": 13.900186538696289, "min": -20.842084884643555, "max": 24.043624877929688, "count": 209 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 209 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 209 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": 0.06361761889927128, "min": -0.25542857162245025, "max": 0.2227913489212861, "count": 209 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 12.278200447559357, "min": -46.77280014753342, "max": 44.30399960279465, "count": 209 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.06361761889927128, "min": -0.25542857162245025, "max": 0.2227913489212861, "count": 209 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 12.278200447559357, "min": -46.77280014753342, "max": 44.30399960279465, "count": 209 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 209 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 209 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.0165368358429987, "min": 0.007948545047353643, "max": 0.023904067111046364, "count": 101 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.0165368358429987, "min": 0.007948545047353643, "max": 0.023904067111046364, "count": 101 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.1125721628467242, "min": 0.08946814537048339, "max": 0.12405024742086729, "count": 101 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.1125721628467242, "min": 0.08946814537048339, "max": 0.12405024742086729, "count": 101 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.11418352921803793, "min": 0.09109867264827093, "max": 0.1264182907839616, "count": 101 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.11418352921803793, "min": 0.09109867264827093, "max": 0.1264182907839616, "count": 101 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 101 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 101 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 101 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 101 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 101 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 101 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1689245844", "python_version": "3.9.17 (main, Jul 5 2023, 20:47:11) [MSC v.1916 64 bit (AMD64)]", "command_line_arguments": "C:\\ProgramData\\anaconda3\\envs\\rlpython\\Scripts\\mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/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": "2.0.1+cpu", "numpy_version": "1.21.2", "end_time_seconds": "1689253155" }, "total": 7311.0283555999995, "count": 1, "self": 0.22450299999945855, "children": { "run_training.setup": { "total": 0.1409528, "count": 1, "self": 0.1409528 }, "TrainerController.start_learning": { "total": 7310.6628998, "count": 1, "self": 3.4980922998493043, "children": { "TrainerController._reset_env": { "total": 5.4822846000012735, "count": 10, "self": 5.4822846000012735 }, "TrainerController.advance": { "total": 7301.5386790001485, "count": 146863, "self": 3.700301000213585, "children": { "env_step": { "total": 2439.0040659999363, "count": 146863, "self": 1894.4940038000395, "children": { "SubprocessEnvManager._take_step": { "total": 542.3075087999578, "count": 146863, "self": 20.220769500017468, "children": { "TorchPolicy.evaluate": { "total": 522.0867392999403, "count": 261486, "self": 522.0867392999403 } } }, "workers": { "total": 2.202553399938852, "count": 146862, "self": 0.0, "children": { "worker_root": { "total": 7300.398557500002, "count": 146862, "is_parallel": true, "self": 5783.223992200098, "children": { "steps_from_proto": { "total": 0.017665900000246815, "count": 20, "is_parallel": true, "self": 0.0035129999989544913, "children": { "_process_rank_one_or_two_observation": { "total": 0.014152900001292323, "count": 80, "is_parallel": true, "self": 0.014152900001292323 } } }, "UnityEnvironment.step": { "total": 1517.1568993999042, "count": 146862, "is_parallel": true, "self": 76.25806909964513, "children": { "UnityEnvironment._generate_step_input": { "total": 51.65471730006807, "count": 146862, "is_parallel": true, "self": 51.65471730006807 }, "communicator.exchange": { "total": 1149.6609378000794, "count": 146862, "is_parallel": true, "self": 1149.6609378000794 }, "steps_from_proto": { "total": 239.5831752001116, "count": 293724, "is_parallel": true, "self": 49.71732580005968, "children": { "_process_rank_one_or_two_observation": { "total": 189.86584940005193, "count": 1174896, "is_parallel": true, "self": 189.86584940005193 } } } } } } } } } } }, "trainer_advance": { "total": 4858.834311999998, "count": 146862, "self": 22.310789500138526, "children": { "process_trajectory": { "total": 1247.532006199859, "count": 146862, "self": 1246.6193053998581, "children": { "RLTrainer._checkpoint": { "total": 0.912700800000934, "count": 5, "self": 0.912700800000934 } } }, "_update_policy": { "total": 3588.9915163, "count": 101, "self": 346.39863790001937, "children": { "TorchPOCAOptimizer.update": { "total": 3242.5928783999807, "count": 3030, "self": 3242.5928783999807 } } } } } } }, "trainer_threads": { "total": 1.100000190490391e-06, "count": 1, "self": 1.100000190490391e-06 }, "TrainerController._save_models": { "total": 0.1438428000001295, "count": 1, "self": 0.0023837999997340376, "children": { "RLTrainer._checkpoint": { "total": 0.14145900000039546, "count": 1, "self": 0.14145900000039546 } } } } } } }