{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4060523509979248, "min": 1.4060523509979248, "max": 1.429282546043396, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 70036.875, "min": 68356.1015625, "max": 78964.015625, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 85.42807625649914, "min": 83.0436974789916, "max": 431.8534482758621, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49292.0, "min": 49166.0, "max": 50095.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999962.0, "min": 49681.0, "max": 1999962.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999962.0, "min": 49681.0, "max": 1999962.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.410193920135498, "min": 0.18605226278305054, "max": 2.4994497299194336, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1390.681884765625, "min": 21.39600944519043, "max": 1456.006591796875, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.720702334954379, "min": 2.0516053552212923, "max": 3.9479791245809417, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2146.8452472686768, "min": 235.9346158504486, "max": 2275.41610121727, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.720702334954379, "min": 2.0516053552212923, "max": 3.9479791245809417, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2146.8452472686768, "min": 235.9346158504486, "max": 2275.41610121727, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.018521856667777885, "min": 0.013167894994937038, "max": 0.02076500644131253, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.055565570003333654, "min": 0.026335789989874077, "max": 0.05631133888770515, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.05883924961090089, "min": 0.01877938242008289, "max": 0.06500912979245185, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.17651774883270266, "min": 0.03755876484016578, "max": 0.19209595521291095, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.6646487784833434e-06, "min": 3.6646487784833434e-06, "max": 0.00029535540154820004, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.099394633545003e-05, "min": 1.099394633545003e-05, "max": 0.0008440975686341499, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10122151666666666, "min": 0.10122151666666666, "max": 0.1984518, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.30366455, "min": 0.20757425000000002, "max": 0.5813658500000001, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 7.095368166666685e-05, "min": 7.095368166666685e-05, "max": 0.004922744820000001, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00021286104500000053, "min": 0.00021286104500000053, "max": 0.014070155915, "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": "1718841324", "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": "2.3.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1718843879" }, "total": 2554.745277434, "count": 1, "self": 0.48433180899974104, "children": { "run_training.setup": { "total": 0.0543304900000976, "count": 1, "self": 0.0543304900000976 }, "TrainerController.start_learning": { "total": 2554.206615135, "count": 1, "self": 4.603154203986378, "children": { "TrainerController._reset_env": { "total": 2.9302859739999576, "count": 1, "self": 2.9302859739999576 }, "TrainerController.advance": { "total": 2546.5600615800136, "count": 232478, "self": 5.0242547069560715, "children": { "env_step": { "total": 2031.7275862130516, "count": 232478, "self": 1678.8713009721405, "children": { "SubprocessEnvManager._take_step": { "total": 349.7552359499048, "count": 232478, "self": 18.105260046866533, "children": { "TorchPolicy.evaluate": { "total": 331.64997590303824, "count": 222964, "self": 331.64997590303824 } } }, "workers": { "total": 3.101049291006234, "count": 232478, "self": 0.0, "children": { "worker_root": { "total": 2546.838383012878, "count": 232478, "is_parallel": true, "self": 1195.727707241812, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.00103639100007058, "count": 1, "is_parallel": true, "self": 0.00027719200011233625, "children": { "_process_rank_one_or_two_observation": { "total": 0.0007591989999582438, "count": 2, "is_parallel": true, "self": 0.0007591989999582438 } } }, "UnityEnvironment.step": { "total": 0.03676444000006995, "count": 1, "is_parallel": true, "self": 0.000588124000046264, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00021195900001202972, "count": 1, "is_parallel": true, "self": 0.00021195900001202972 }, "communicator.exchange": { "total": 0.035045181999976194, "count": 1, "is_parallel": true, "self": 0.035045181999976194 }, "steps_from_proto": { "total": 0.0009191750000354659, "count": 1, "is_parallel": true, "self": 0.0002694190000056551, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006497560000298108, "count": 2, "is_parallel": true, "self": 0.0006497560000298108 } } } } } } }, "UnityEnvironment.step": { "total": 1351.1106757710659, "count": 232477, "is_parallel": true, "self": 40.37772050197373, "children": { "UnityEnvironment._generate_step_input": { "total": 89.37881037006582, "count": 232477, "is_parallel": true, "self": 89.37881037006582 }, "communicator.exchange": { "total": 1125.9572015040408, "count": 232477, "is_parallel": true, "self": 1125.9572015040408 }, "steps_from_proto": { "total": 95.39694339498567, "count": 232477, "is_parallel": true, "self": 36.504365222924775, "children": { "_process_rank_one_or_two_observation": { "total": 58.892578172060894, "count": 464954, "is_parallel": true, "self": 58.892578172060894 } } } } } } } } } } }, "trainer_advance": { "total": 509.80822066000576, "count": 232478, "self": 6.993247761041971, "children": { "process_trajectory": { "total": 164.80673192696383, "count": 232478, "self": 163.5474330759639, "children": { "RLTrainer._checkpoint": { "total": 1.259298850999926, "count": 10, "self": 1.259298850999926 } } }, "_update_policy": { "total": 338.00824097199995, "count": 97, "self": 273.80596892000233, "children": { "TorchPPOOptimizer.update": { "total": 64.20227205199762, "count": 2910, "self": 64.20227205199762 } } } } } } }, "trainer_threads": { "total": 9.85000042419415e-07, "count": 1, "self": 9.85000042419415e-07 }, "TrainerController._save_models": { "total": 0.11311239199994816, "count": 1, "self": 0.001925745000335155, "children": { "RLTrainer._checkpoint": { "total": 0.111186646999613, "count": 1, "self": 0.111186646999613 } } } } } } }