{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 2.6255717277526855, "min": 2.0630123615264893, "max": 3.2957704067230225, "count": 722 }, "SoccerTwos.Policy.Entropy.sum": { "value": 33943.390625, "min": 13144.6884765625, "max": 120854.34375, "count": 722 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 999.0, "min": 423.8333333333333, "max": 999.0, "count": 722 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19980.0, "min": 10172.0, "max": 31324.0, "count": 722 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1195.7372710068555, "min": 1195.7372710068555, "max": 1209.0615775276597, "count": 87 }, "SoccerTwos.Self-play.ELO.sum": { "value": 4782.949084027422, "min": 2391.4808618080865, "max": 14464.36146440959, "count": 87 }, "SoccerTwos.Step.mean": { "value": 7219028.0, "min": 9678.0, "max": 7219028.0, "count": 722 }, "SoccerTwos.Step.sum": { "value": 7219028.0, "min": 9678.0, "max": 7219028.0, "count": 722 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": 0.002083804691210389, "min": -0.035258762538433075, "max": 0.04194639250636101, "count": 722 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": 0.020838046446442604, "min": -0.599292516708374, "max": 0.4194639325141907, "count": 722 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": 0.0018059492576867342, "min": -0.03531572222709656, "max": 0.029078194871544838, "count": 722 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": 0.018059492111206055, "min": -0.6001506447792053, "max": 0.2907819449901581, "count": 722 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 722 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 722 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": 0.044679999351501465, "min": -0.5, "max": 0.2465666631857554, "count": 722 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 0.44679999351501465, "min": -6.0, "max": 2.958799958229065, "count": 722 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.044679999351501465, "min": -0.5, "max": 0.2465666631857554, "count": 722 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 0.44679999351501465, "min": -6.0, "max": 2.958799958229065, "count": 722 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 722 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 722 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.016023726199637166, "min": 0.00859238493333881, "max": 0.02290575326284549, "count": 330 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.016023726199637166, "min": 0.00859238493333881, "max": 0.02290575326284549, "count": 330 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.0025711507769301534, "min": 3.3094705494581454e-10, "max": 0.0053011750729638155, "count": 330 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.0025711507769301534, "min": 3.3094705494581454e-10, "max": 0.0053011750729638155, "count": 330 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.002575425039200733, "min": 2.352361768339269e-10, "max": 0.0052358094952069225, "count": 330 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.002575425039200733, "min": 2.352361768339269e-10, "max": 0.0052358094952069225, "count": 330 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 330 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 330 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.2, "max": 0.20000000000000007, "count": 330 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.2, "max": 0.20000000000000007, "count": 330 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 330 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 330 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1716391090", "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\\RAY\\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": "2.3.0+cpu", "numpy_version": "1.23.5", "end_time_seconds": "1716409918" }, "total": 18827.914496999932, "count": 1, "self": 10.012552099884488, "children": { "run_training.setup": { "total": 0.2577732000499964, "count": 1, "self": 0.2577732000499964 }, "TrainerController.start_learning": { "total": 18817.644171699998, "count": 1, "self": 12.035114099970087, "children": { "TrainerController._reset_env": { "total": 32.076831100159325, "count": 36, "self": 32.076831100159325 }, "TrainerController.advance": { "total": 18773.356785099953, "count": 469309, "self": 10.246123759192415, "children": { "env_step": { "total": 8385.282620415208, "count": 469309, "self": 6575.170129238279, "children": { "SubprocessEnvManager._take_step": { "total": 1802.591238191002, "count": 469309, "self": 58.34078842587769, "children": { "TorchPolicy.evaluate": { "total": 1744.2504497651244, "count": 932452, "self": 1744.2504497651244 } } }, "workers": { "total": 7.521252985927276, "count": 469308, "self": 0.0, "children": { "worker_root": { "total": 18776.14601170807, "count": 469308, "is_parallel": true, "self": 13706.473688248429, "children": { "steps_from_proto": { "total": 0.0795829005073756, "count": 72, "is_parallel": true, "self": 0.01388260128442198, "children": { "_process_rank_one_or_two_observation": { "total": 0.06570029922295362, "count": 288, "is_parallel": true, "self": 0.06570029922295362 } } }, "UnityEnvironment.step": { "total": 5069.592740559136, "count": 469308, "is_parallel": true, "self": 294.45154071133584, "children": { "UnityEnvironment._generate_step_input": { "total": 268.2372855601134, "count": 469308, "is_parallel": true, "self": 268.2372855601134 }, "communicator.exchange": { "total": 3575.3558380041504, "count": 469308, "is_parallel": true, "self": 3575.3558380041504 }, "steps_from_proto": { "total": 931.5480762835359, "count": 938616, "is_parallel": true, "self": 178.8616694076918, "children": { "_process_rank_one_or_two_observation": { "total": 752.6864068758441, "count": 3754464, "is_parallel": true, "self": 752.6864068758441 } } } } } } } } } } }, "trainer_advance": { "total": 10377.828040925553, "count": 469308, "self": 108.16009088198189, "children": { "process_trajectory": { "total": 1403.0475844438188, "count": 469308, "self": 1401.1869686435675, "children": { "RLTrainer._checkpoint": { "total": 1.860615800251253, "count": 14, "self": 1.860615800251253 } } }, "_update_policy": { "total": 8866.620365599752, "count": 331, "self": 1083.231060908176, "children": { "TorchPOCAOptimizer.update": { "total": 7783.389304691576, "count": 9933, "self": 7783.389304691576 } } } } } } }, "trainer_threads": { "total": 2.00001522898674e-06, "count": 1, "self": 2.00001522898674e-06 }, "TrainerController._save_models": { "total": 0.17543939989991486, "count": 1, "self": 0.041915099951438606, "children": { "RLTrainer._checkpoint": { "total": 0.13352429994847625, "count": 1, "self": 0.13352429994847625 } } } } } } }