{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.3987538814544678, "min": 1.3987538814544678, "max": 1.426681637763977, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 70760.1640625, "min": 67626.8984375, "max": 77275.578125, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 106.7056277056277, "min": 84.43174061433447, "max": 404.0, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49298.0, "min": 48871.0, "max": 50500.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999959.0, "min": 49875.0, "max": 1999959.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999959.0, "min": 49875.0, "max": 1999959.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.331249713897705, "min": 0.07285147905349731, "max": 2.415976047515869, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1077.037353515625, "min": 9.033583641052246, "max": 1378.555419921875, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.50783913901874, "min": 1.6180255115032196, "max": 3.9550276264986572, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 1620.6216822266579, "min": 200.63516342639923, "max": 2194.4163081645966, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.50783913901874, "min": 1.6180255115032196, "max": 3.9550276264986572, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 1620.6216822266579, "min": 200.63516342639923, "max": 2194.4163081645966, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.017430648175973652, "min": 0.013040787393705008, "max": 0.019770269141008615, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.05229194452792096, "min": 0.026081574787410015, "max": 0.05631267793796724, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.047199703007936473, "min": 0.022328181502719723, "max": 0.061978931352496144, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.14159910902380943, "min": 0.044656363005439445, "max": 0.18240834064781666, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.3387988870999948e-06, "min": 3.3387988870999948e-06, "max": 0.00029534872655042504, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.0016396661299984e-05, "min": 1.0016396661299984e-05, "max": 0.00084381376872875, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10111289999999999, "min": 0.10111289999999999, "max": 0.19844957500000004, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.30333869999999996, "min": 0.20735644999999997, "max": 0.5812712499999999, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 6.553370999999993e-05, "min": 6.553370999999993e-05, "max": 0.004922633792499999, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00019660112999999978, "min": 0.00019660112999999978, "max": 0.014065435374999997, "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": "1671441079", "python_version": "3.8.16 (default, Dec 7 2022, 01:12:13) \n[GCC 7.5.0]", "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": "0.29.0.dev0", "mlagents_envs_version": "0.29.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.8.1+cu102", "numpy_version": "1.21.6", "end_time_seconds": "1671443256" }, "total": 2176.987539207, "count": 1, "self": 0.43803955400017003, "children": { "run_training.setup": { "total": 0.11170091899998624, "count": 1, "self": 0.11170091899998624 }, "TrainerController.start_learning": { "total": 2176.437798734, "count": 1, "self": 3.8043411908911366, "children": { "TrainerController._reset_env": { "total": 7.809492422999938, "count": 1, "self": 7.809492422999938 }, "TrainerController.advance": { "total": 2164.707123833109, "count": 232127, "self": 3.9731883631493474, "children": { "env_step": { "total": 1703.2867811050007, "count": 232127, "self": 1427.7233516291917, "children": { "SubprocessEnvManager._take_step": { "total": 273.0700935929774, "count": 232127, "self": 13.95705414696829, "children": { "TorchPolicy.evaluate": { "total": 259.1130394460091, "count": 223074, "self": 64.41122065296634, "children": { "TorchPolicy.sample_actions": { "total": 194.70181879304278, "count": 223074, "self": 194.70181879304278 } } } } }, "workers": { "total": 2.493335882831502, "count": 232127, "self": 0.0, "children": { "worker_root": { "total": 2168.8474170630247, "count": 232127, "is_parallel": true, "self": 991.452439668042, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002172009999981128, "count": 1, "is_parallel": true, "self": 0.0003550100000211387, "children": { "_process_rank_one_or_two_observation": { "total": 0.0018169999999599895, "count": 2, "is_parallel": true, "self": 0.0018169999999599895 } } }, "UnityEnvironment.step": { "total": 0.028565380000031837, "count": 1, "is_parallel": true, "self": 0.0004244140001219421, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00016922499992233497, "count": 1, "is_parallel": true, "self": 0.00016922499992233497 }, "communicator.exchange": { "total": 0.02722527599996738, "count": 1, "is_parallel": true, "self": 0.02722527599996738 }, "steps_from_proto": { "total": 0.00074646500002018, "count": 1, "is_parallel": true, "self": 0.0002541930000461434, "children": { "_process_rank_one_or_two_observation": { "total": 0.0004922719999740366, "count": 2, "is_parallel": true, "self": 0.0004922719999740366 } } } } } } }, "UnityEnvironment.step": { "total": 1177.3949773949828, "count": 232126, "is_parallel": true, "self": 34.693501372103356, "children": { "UnityEnvironment._generate_step_input": { "total": 74.3945290439143, "count": 232126, "is_parallel": true, "self": 74.3945290439143 }, "communicator.exchange": { "total": 977.0267700610148, "count": 232126, "is_parallel": true, "self": 977.0267700610148 }, "steps_from_proto": { "total": 91.28017691795048, "count": 232126, "is_parallel": true, "self": 37.418301526947744, "children": { "_process_rank_one_or_two_observation": { "total": 53.86187539100274, "count": 464252, "is_parallel": true, "self": 53.86187539100274 } } } } } } } } } } }, "trainer_advance": { "total": 457.44715436495926, "count": 232127, "self": 5.686067214890954, "children": { "process_trajectory": { "total": 143.08526061807038, "count": 232127, "self": 141.9132922750714, "children": { "RLTrainer._checkpoint": { "total": 1.17196834299898, "count": 10, "self": 1.17196834299898 } } }, "_update_policy": { "total": 308.6758265319979, "count": 97, "self": 255.75351716801742, "children": { "TorchPPOOptimizer.update": { "total": 52.9223093639805, "count": 2910, "self": 52.9223093639805 } } } } } } }, "trainer_threads": { "total": 9.139998837781604e-07, "count": 1, "self": 9.139998837781604e-07 }, "TrainerController._save_models": { "total": 0.11684037299983174, "count": 1, "self": 0.0019047949995183444, "children": { "RLTrainer._checkpoint": { "total": 0.1149355780003134, "count": 1, "self": 0.1149355780003134 } } } } } } }