{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.5814601182937622, "min": 1.5709996223449707, "max": 3.29571795463562, "count": 1226 }, "SoccerTwos.Policy.Entropy.sum": { "value": 32944.9765625, "min": 14226.4921875, "max": 124715.2421875, "count": 1226 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 69.78571428571429, "min": 45.211009174311926, "max": 999.0, "count": 1226 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19540.0, "min": 16536.0, "max": 23764.0, "count": 1226 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1695.9962599859766, "min": 1195.4260022115066, "max": 1739.5694497428608, "count": 1219 }, "SoccerTwos.Self-play.ELO.sum": { "value": 237439.47639803673, "min": 2390.852004423013, "max": 345672.31398027134, "count": 1219 }, "SoccerTwos.Step.mean": { "value": 12259994.0, "min": 9662.0, "max": 12259994.0, "count": 1226 }, "SoccerTwos.Step.sum": { "value": 12259994.0, "min": 9662.0, "max": 12259994.0, "count": 1226 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.03554478660225868, "min": -0.11080346256494522, "max": 0.22602124512195587, "count": 1226 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -4.9762701988220215, "min": -18.947391510009766, "max": 25.31437873840332, "count": 1226 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.03543717414140701, "min": -0.11030250787734985, "max": 0.22332414984703064, "count": 1226 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -4.961204528808594, "min": -18.86172866821289, "max": 25.012304306030273, "count": 1226 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 1226 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 1226 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": 0.004299999986376081, "min": -0.5285250023007393, "max": 0.43070588392369885, "count": 1226 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 0.6019999980926514, "min": -53.013999819755554, "max": 51.096800446510315, "count": 1226 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.004299999986376081, "min": -0.5285250023007393, "max": 0.43070588392369885, "count": 1226 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 0.6019999980926514, "min": -53.013999819755554, "max": 51.096800446510315, "count": 1226 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 1226 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 1226 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.018027735963308564, "min": 0.012588491471251472, "max": 0.02550934345150987, "count": 592 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.018027735963308564, "min": 0.012588491471251472, "max": 0.02550934345150987, "count": 592 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.09308374772469202, "min": 0.000641497738736992, "max": 0.10492393299937249, "count": 592 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.09308374772469202, "min": 0.000641497738736992, "max": 0.10492393299937249, "count": 592 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.09485623612999916, "min": 0.0006961862221942283, "max": 0.10865654771526655, "count": 592 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.09485623612999916, "min": 0.0006961862221942283, "max": 0.10865654771526655, "count": 592 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 592 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 592 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 592 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 592 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 592 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 592 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1701316047", "python_version": "3.10.11 (tags/v3.10.11:7d4cc5a, Apr 5 2023, 00:38:17) [MSC v.1929 64 bit (AMD64)]", "command_line_arguments": "\\\\?\\D:\\Masters\\Git_repo\\RL_MultiAgent\\.venv_RL\\Scripts\\mlagents-learn ./config/poca/SoccerTwos.yaml --env=./SoccerTwos/SoccerTwos/SoccerTwos.exe --run-id=SoccerTwos-v3 --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.1.1+cpu", "numpy_version": "1.23.5", "end_time_seconds": "1701360831" }, "total": 44783.34479589999, "count": 1, "self": 2.016953799990006, "children": { "run_training.setup": { "total": 0.22558690002188087, "count": 1, "self": 0.22558690002188087 }, "TrainerController.start_learning": { "total": 44781.10225519998, "count": 1, "self": 23.013502790417988, "children": { "TrainerController._reset_env": { "total": 10.372097299841698, "count": 62, "self": 10.372097299841698 }, "TrainerController.advance": { "total": 44747.4374435097, "count": 836923, "self": 23.138725397002418, "children": { "env_step": { "total": 20235.061383585155, "count": 836923, "self": 15920.225197862717, "children": { "SubprocessEnvManager._take_step": { "total": 4299.914687429438, "count": 836923, "self": 132.96157608472276, "children": { "TorchPolicy.evaluate": { "total": 4166.953111344716, "count": 1543588, "self": 4166.953111344716 } } }, "workers": { "total": 14.921498292998876, "count": 836923, "self": 0.0, "children": { "worker_root": { "total": 44712.18858607486, "count": 836923, "is_parallel": true, "self": 31555.166479885927, "children": { "steps_from_proto": { "total": 0.1742748999968171, "count": 124, "is_parallel": true, "self": 0.025308399694040418, "children": { "_process_rank_one_or_two_observation": { "total": 0.1489665003027767, "count": 496, "is_parallel": true, "self": 0.1489665003027767 } } }, "UnityEnvironment.step": { "total": 13156.847831288935, "count": 836923, "is_parallel": true, "self": 636.4406358192209, "children": { "UnityEnvironment._generate_step_input": { "total": 474.4725101144286, "count": 836923, "is_parallel": true, "self": 474.4725101144286 }, "communicator.exchange": { "total": 10043.83046678803, "count": 836923, "is_parallel": true, "self": 10043.83046678803 }, "steps_from_proto": { "total": 2002.1042185672559, "count": 1673846, "is_parallel": true, "self": 382.71403283649124, "children": { "_process_rank_one_or_two_observation": { "total": 1619.3901857307646, "count": 6695384, "is_parallel": true, "self": 1619.3901857307646 } } } } } } } } } } }, "trainer_advance": { "total": 24489.23733452754, "count": 836923, "self": 168.33715212979587, "children": { "process_trajectory": { "total": 4440.888958397089, "count": 836923, "self": 4432.874032397172, "children": { "RLTrainer._checkpoint": { "total": 8.014925999916159, "count": 24, "self": 8.014925999916159 } } }, "_update_policy": { "total": 19880.011224000657, "count": 593, "self": 1846.678185804456, "children": { "TorchPOCAOptimizer.update": { "total": 18033.3330381962, "count": 17776, "self": 18033.3330381962 } } } } } } }, "trainer_threads": { "total": 1.500011421740055e-06, "count": 1, "self": 1.500011421740055e-06 }, "TrainerController._save_models": { "total": 0.27921010000864044, "count": 1, "self": 0.017044999985955656, "children": { "RLTrainer._checkpoint": { "total": 0.2621651000226848, "count": 1, "self": 0.2621651000226848 } } } } } } }