{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4057353734970093, "min": 1.4057353734970093, "max": 1.4298509359359741, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 69994.375, "min": 67764.0, "max": 78830.78125, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 96.42105263157895, "min": 86.15183246073299, "max": 391.9453125, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49464.0, "min": 48949.0, "max": 50169.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999980.0, "min": 49601.0, "max": 1999980.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999980.0, "min": 49601.0, "max": 1999980.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.3798208236694336, "min": 0.17059510946273804, "max": 2.4268596172332764, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1220.8480224609375, "min": 21.665578842163086, "max": 1375.174560546875, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.687070602445807, "min": 1.7603671414645639, "max": 3.8601367199775014, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 1891.467219054699, "min": 223.5666269659996, "max": 2166.153334081173, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.687070602445807, "min": 1.7603671414645639, "max": 3.8601367199775014, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 1891.467219054699, "min": 223.5666269659996, "max": 2166.153334081173, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.017722960558926894, "min": 0.013144492062080342, "max": 0.01970972528158907, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.05316888167678068, "min": 0.026288984124160683, "max": 0.05912917584476721, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.05016221354405085, "min": 0.021540686519195634, "max": 0.06116366961763966, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.15048664063215256, "min": 0.04308137303839127, "max": 0.18349100885291897, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.3012988996000034e-06, "min": 3.3012988996000034e-06, "max": 0.0002953209765596749, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 9.90389669880001e-06, "min": 9.90389669880001e-06, "max": 0.0008440905186364999, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10110040000000002, "min": 0.10110040000000002, "max": 0.198440325, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.30330120000000005, "min": 0.2073293, "max": 0.5813635000000001, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 6.490996000000008e-05, "min": 6.490996000000008e-05, "max": 0.0049221722175, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00019472988000000024, "min": 0.00019472988000000024, "max": 0.014070038650000002, "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": "1673354780", "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": "1673359758" }, "total": 4977.296750438, "count": 1, "self": 0.6135134000005564, "children": { "run_training.setup": { "total": 0.1610328550000304, "count": 1, "self": 0.1610328550000304 }, "TrainerController.start_learning": { "total": 4976.522204182999, "count": 1, "self": 8.932847856117405, "children": { "TrainerController._reset_env": { "total": 6.034937672999945, "count": 1, "self": 6.034937672999945 }, "TrainerController.advance": { "total": 4961.361065979882, "count": 231618, "self": 8.458412705196679, "children": { "env_step": { "total": 3269.77078050283, "count": 231618, "self": 2784.395340785581, "children": { "SubprocessEnvManager._take_step": { "total": 478.88726788706583, "count": 231618, "self": 32.61589710880946, "children": { "TorchPolicy.evaluate": { "total": 446.27137077825637, "count": 222858, "self": 67.39098456416514, "children": { "TorchPolicy.sample_actions": { "total": 378.88038621409123, "count": 222858, "self": 378.88038621409123 } } } } }, "workers": { "total": 6.4881718301830915, "count": 231618, "self": 0.0, "children": { "worker_root": { "total": 4957.8727447270385, "count": 231618, "is_parallel": true, "self": 2696.131931449195, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0026382290000128705, "count": 1, "is_parallel": true, "self": 0.0004593920000388607, "children": { "_process_rank_one_or_two_observation": { "total": 0.00217883699997401, "count": 2, "is_parallel": true, "self": 0.00217883699997401 } } }, "UnityEnvironment.step": { "total": 0.0390804040000603, "count": 1, "is_parallel": true, "self": 0.00037474199996268, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0002552170000171827, "count": 1, "is_parallel": true, "self": 0.0002552170000171827 }, "communicator.exchange": { "total": 0.037461355000004914, "count": 1, "is_parallel": true, "self": 0.037461355000004914 }, "steps_from_proto": { "total": 0.000989090000075521, "count": 1, "is_parallel": true, "self": 0.00031493200003751554, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006741580000380054, "count": 2, "is_parallel": true, "self": 0.0006741580000380054 } } } } } } }, "UnityEnvironment.step": { "total": 2261.7408132778437, "count": 231617, "is_parallel": true, "self": 65.62979042882262, "children": { "UnityEnvironment._generate_step_input": { "total": 96.53612441980181, "count": 231617, "is_parallel": true, "self": 96.53612441980181 }, "communicator.exchange": { "total": 1935.8028796440885, "count": 231617, "is_parallel": true, "self": 1935.8028796440885 }, "steps_from_proto": { "total": 163.77201878513074, "count": 231617, "is_parallel": true, "self": 61.29172527704418, "children": { "_process_rank_one_or_two_observation": { "total": 102.48029350808656, "count": 463234, "is_parallel": true, "self": 102.48029350808656 } } } } } } } } } } }, "trainer_advance": { "total": 1683.1318727718558, "count": 231618, "self": 15.458389020965342, "children": { "process_trajectory": { "total": 275.18927695288653, "count": 231618, "self": 273.70834820188793, "children": { "RLTrainer._checkpoint": { "total": 1.4809287509986007, "count": 10, "self": 1.4809287509986007 } } }, "_update_policy": { "total": 1392.484206798004, "count": 97, "self": 355.9358637280079, "children": { "TorchPPOOptimizer.update": { "total": 1036.548343069996, "count": 2910, "self": 1036.548343069996 } } } } } } }, "trainer_threads": { "total": 1.100000190490391e-06, "count": 1, "self": 1.100000190490391e-06 }, "TrainerController._save_models": { "total": 0.19335157399927994, "count": 1, "self": 0.005382831999668269, "children": { "RLTrainer._checkpoint": { "total": 0.18796874199961167, "count": 1, "self": 0.18796874199961167 } } } } } } }