{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.3986353874206543, "min": 1.3986353874206543, "max": 1.4287108182907104, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 70026.875, "min": 68254.578125, "max": 77575.46875, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 73.24962852897474, "min": 66.27860026917901, "max": 387.2325581395349, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49297.0, "min": 49235.0, "max": 50194.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999937.0, "min": 49991.0, "max": 1999937.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999937.0, "min": 49991.0, "max": 1999937.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.504150152206421, "min": 0.085252545773983, "max": 2.554262161254883, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1685.2930908203125, "min": 10.912325859069824, "max": 1862.4368896484375, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.8538110529862752, "min": 1.8701692037284374, "max": 4.078108948392198, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2593.6148386597633, "min": 239.38165807724, "max": 2900.2680180072784, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.8538110529862752, "min": 1.8701692037284374, "max": 4.078108948392198, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2593.6148386597633, "min": 239.38165807724, "max": 2900.2680180072784, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.01713411754010142, "min": 0.013020315719071127, "max": 0.019621831697360093, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.05140235262030426, "min": 0.026040631438142253, "max": 0.05886549509208028, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.06439653010004097, "min": 0.02235464934880535, "max": 0.06485258162849479, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.1931895903001229, "min": 0.0447092986976107, "max": 0.19455774488548436, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 4.027798657433334e-06, "min": 4.027798657433334e-06, "max": 0.0002953152015616001, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.2083395972300003e-05, "min": 1.2083395972300003e-05, "max": 0.00084403636865455, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10134256666666668, "min": 0.10134256666666668, "max": 0.19843839999999996, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.3040277, "min": 0.20781884999999994, "max": 0.5813454499999999, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 7.69940766666667e-05, "min": 7.69940766666667e-05, "max": 0.004922076160000002, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00023098223000000008, "min": 0.00023098223000000008, "max": 0.014069137954999996, "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": "1700795955", "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [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=Huggy --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.1.0+cu118", "numpy_version": "1.23.5", "end_time_seconds": "1700798631" }, "total": 2676.273168921, "count": 1, "self": 0.42571384300026693, "children": { "run_training.setup": { "total": 0.09215004699996143, "count": 1, "self": 0.09215004699996143 }, "TrainerController.start_learning": { "total": 2675.755305031, "count": 1, "self": 4.917879433987309, "children": { "TrainerController._reset_env": { "total": 9.534449709, "count": 1, "self": 9.534449709 }, "TrainerController.advance": { "total": 2661.2053214870125, "count": 233996, "self": 5.184322640030587, "children": { "env_step": { "total": 2112.535270195023, "count": 233996, "self": 1739.399344762064, "children": { "SubprocessEnvManager._take_step": { "total": 369.9809297279243, "count": 233996, "self": 17.922718446952786, "children": { "TorchPolicy.evaluate": { "total": 352.05821128097153, "count": 222976, "self": 352.05821128097153 } } }, "workers": { "total": 3.15499570503448, "count": 233996, "self": 0.0, "children": { "worker_root": { "total": 2667.9075967770536, "count": 233996, "is_parallel": true, "self": 1258.6412715610063, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0008799550000162526, "count": 1, "is_parallel": true, "self": 0.0002652079999734269, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006147470000428257, "count": 2, "is_parallel": true, "self": 0.0006147470000428257 } } }, "UnityEnvironment.step": { "total": 0.06590278999999555, "count": 1, "is_parallel": true, "self": 0.00033837399996627937, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0002013330000067981, "count": 1, "is_parallel": true, "self": 0.0002013330000067981 }, "communicator.exchange": { "total": 0.06457055700002456, "count": 1, "is_parallel": true, "self": 0.06457055700002456 }, "steps_from_proto": { "total": 0.0007925259999979062, "count": 1, "is_parallel": true, "self": 0.00020989199998666663, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005826340000112396, "count": 2, "is_parallel": true, "self": 0.0005826340000112396 } } } } } } }, "UnityEnvironment.step": { "total": 1409.2663252160473, "count": 233995, "is_parallel": true, "self": 42.23556139100651, "children": { "UnityEnvironment._generate_step_input": { "total": 93.0308111700478, "count": 233995, "is_parallel": true, "self": 93.0308111700478 }, "communicator.exchange": { "total": 1176.560380420091, "count": 233995, "is_parallel": true, "self": 1176.560380420091 }, "steps_from_proto": { "total": 97.43957223490202, "count": 233995, "is_parallel": true, "self": 37.028750730861645, "children": { "_process_rank_one_or_two_observation": { "total": 60.41082150404037, "count": 467990, "is_parallel": true, "self": 60.41082150404037 } } } } } } } } } } }, "trainer_advance": { "total": 543.4857286519592, "count": 233996, "self": 6.972994251983778, "children": { "process_trajectory": { "total": 182.74190483197617, "count": 233996, "self": 181.53592664497705, "children": { "RLTrainer._checkpoint": { "total": 1.2059781869991184, "count": 10, "self": 1.2059781869991184 } } }, "_update_policy": { "total": 353.7708295679993, "count": 97, "self": 289.3172194410049, "children": { "TorchPPOOptimizer.update": { "total": 64.45361012699436, "count": 2910, "self": 64.45361012699436 } } } } } } }, "trainer_threads": { "total": 9.43000031838892e-07, "count": 1, "self": 9.43000031838892e-07 }, "TrainerController._save_models": { "total": 0.09765345799996794, "count": 1, "self": 0.001874084000064613, "children": { "RLTrainer._checkpoint": { "total": 0.09577937399990333, "count": 1, "self": 0.09577937399990333 } } } } } } }