{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.3980318307876587, "min": 1.3980318307876587, "max": 1.4248502254486084, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 69106.109375, "min": 68297.078125, "max": 78705.03125, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 76.75, "min": 74.45921450151057, "max": 375.09022556390977, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49427.0, "min": 49004.0, "max": 50032.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999996.0, "min": 49469.0, "max": 1999996.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999996.0, "min": 49469.0, "max": 1999996.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.470482349395752, "min": 0.13963332772254944, "max": 2.509178400039673, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1590.9906005859375, "min": 18.431598663330078, "max": 1619.9735107421875, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.7889638361723526, "min": 1.8084204251115972, "max": 3.995734997210093, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2440.092710494995, "min": 238.71149611473083, "max": 2494.581487953663, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.7889638361723526, "min": 1.8084204251115972, "max": 3.995734997210093, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2440.092710494995, "min": 238.71149611473083, "max": 2494.581487953663, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.01580044502528229, "min": 0.013987934851502359, "max": 0.020327170274807335, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.04740133507584687, "min": 0.027975869703004717, "max": 0.060981510824422006, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.06207135129306051, "min": 0.02053013217325012, "max": 0.06462156555304925, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.18621405387918152, "min": 0.04106026434650024, "max": 0.1882140550762415, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.895948701383334e-06, "min": 3.895948701383334e-06, "max": 0.000295376776541075, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.1687846104150002e-05, "min": 1.1687846104150002e-05, "max": 0.00084414646861785, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10129861666666666, "min": 0.10129861666666666, "max": 0.19845892500000006, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.30389584999999997, "min": 0.20774245, "max": 0.5813821499999999, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 7.480097166666668e-05, "min": 7.480097166666668e-05, "max": 0.004923100357500001, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00022440291500000007, "min": 0.00022440291500000007, "max": 0.014070969284999997, "count": 40 }, "Huggy.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 40 }, "Huggy.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 40 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1715434553", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/Huggy.yaml --env=./trained-envs-executables/linux/Huggy/Huggy --run-id=Huggy2 --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+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1715437132" }, "total": 2579.664495321, "count": 1, "self": 0.438086189999467, "children": { "run_training.setup": { "total": 0.054723072000001594, "count": 1, "self": 0.054723072000001594 }, "TrainerController.start_learning": { "total": 2579.1716860590004, "count": 1, "self": 5.006586613101263, "children": { "TrainerController._reset_env": { "total": 3.0335532550000153, "count": 1, "self": 3.0335532550000153 }, "TrainerController.advance": { "total": 2571.0113329638993, "count": 232869, "self": 5.261062567073623, "children": { "env_step": { "total": 2037.3508296958412, "count": 232869, "self": 1683.0311916961082, "children": { "SubprocessEnvManager._take_step": { "total": 351.0608525008571, "count": 232869, "self": 18.06952413392412, "children": { "TorchPolicy.evaluate": { "total": 332.991328366933, "count": 222874, "self": 332.991328366933 } } }, "workers": { "total": 3.258785498875909, "count": 232869, "self": 0.0, "children": { "worker_root": { "total": 2571.5535545529915, "count": 232869, "is_parallel": true, "self": 1219.2628207019227, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0008696890000692292, "count": 1, "is_parallel": true, "self": 0.00022650000005342008, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006431890000158091, "count": 2, "is_parallel": true, "self": 0.0006431890000158091 } } }, "UnityEnvironment.step": { "total": 0.029327101999911065, "count": 1, "is_parallel": true, "self": 0.00040543599970988, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00023559300007036654, "count": 1, "is_parallel": true, "self": 0.00023559300007036654 }, "communicator.exchange": { "total": 0.027919304000079137, "count": 1, "is_parallel": true, "self": 0.027919304000079137 }, "steps_from_proto": { "total": 0.0007667690000516814, "count": 1, "is_parallel": true, "self": 0.00019790400006058917, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005688649999910922, "count": 2, "is_parallel": true, "self": 0.0005688649999910922 } } } } } } }, "UnityEnvironment.step": { "total": 1352.2907338510688, "count": 232868, "is_parallel": true, "self": 41.1686630629938, "children": { "UnityEnvironment._generate_step_input": { "total": 83.6599897119836, "count": 232868, "is_parallel": true, "self": 83.6599897119836 }, "communicator.exchange": { "total": 1131.870991206061, "count": 232868, "is_parallel": true, "self": 1131.870991206061 }, "steps_from_proto": { "total": 95.59108987003037, "count": 232868, "is_parallel": true, "self": 33.47987024698864, "children": { "_process_rank_one_or_two_observation": { "total": 62.111219623041734, "count": 465736, "is_parallel": true, "self": 62.111219623041734 } } } } } } } } } } }, "trainer_advance": { "total": 528.3994407009845, "count": 232869, "self": 7.336565701947848, "children": { "process_trajectory": { "total": 169.6801916470364, "count": 232869, "self": 168.07445709603655, "children": { "RLTrainer._checkpoint": { "total": 1.6057345509998413, "count": 10, "self": 1.6057345509998413 } } }, "_update_policy": { "total": 351.3826833520003, "count": 97, "self": 284.26801983199596, "children": { "TorchPPOOptimizer.update": { "total": 67.11466352000434, "count": 2910, "self": 67.11466352000434 } } } } } } }, "trainer_threads": { "total": 7.579997145512607e-07, "count": 1, "self": 7.579997145512607e-07 }, "TrainerController._save_models": { "total": 0.12021246899985272, "count": 1, "self": 0.003229428999929951, "children": { "RLTrainer._checkpoint": { "total": 0.11698303999992277, "count": 1, "self": 0.11698303999992277 } } } } } } }