{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4115371704101562, "min": 1.4115371704101562, "max": 1.4304763078689575, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 69306.4765625, "min": 68988.7890625, "max": 76478.390625, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 89.45207956600362, "min": 80.2183908045977, "max": 391.8203125, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49467.0, "min": 48766.0, "max": 50153.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999923.0, "min": 49940.0, "max": 1999923.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999923.0, "min": 49940.0, "max": 1999923.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.3586559295654297, "min": 0.131281778216362, "max": 2.45984148979187, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1304.3367919921875, "min": 16.672786712646484, "max": 1469.0914306640625, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.667770275047847, "min": 2.0512009913057794, "max": 3.920948320563803, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2028.2769621014595, "min": 260.50252589583397, "max": 2278.98466783762, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.667770275047847, "min": 2.0512009913057794, "max": 3.920948320563803, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2028.2769621014595, "min": 260.50252589583397, "max": 2278.98466783762, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.016899755167024622, "min": 0.013661170341947582, "max": 0.020558865014027105, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.05069926550107387, "min": 0.027322340683895163, "max": 0.06064619927953269, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.05638637008766333, "min": 0.021339635054270428, "max": 0.07188540132095417, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.16915911026299, "min": 0.042679270108540855, "max": 0.18488538240393004, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.1050489650166726e-06, "min": 3.1050489650166726e-06, "max": 0.00029532510155830005, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 9.315146895050018e-06, "min": 9.315146895050018e-06, "max": 0.0008440908186364, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10103498333333334, "min": 0.10103498333333334, "max": 0.19844169999999994, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.30310495000000004, "min": 0.20728210000000002, "max": 0.5813636000000001, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 6.164566833333344e-05, "min": 6.164566833333344e-05, "max": 0.004922240830000001, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00018493700500000034, "min": 0.00018493700500000034, "max": 0.014070043639999998, "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": "1670439861", "python_version": "3.8.15 (default, Oct 12 2022, 19:14:39) \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": "1670442269" }, "total": 2408.161839026, "count": 1, "self": 0.39296544199987693, "children": { "run_training.setup": { "total": 0.11611243699996976, "count": 1, "self": 0.11611243699996976 }, "TrainerController.start_learning": { "total": 2407.652761147, "count": 1, "self": 4.15853305706878, "children": { "TrainerController._reset_env": { "total": 9.441568495999945, "count": 1, "self": 9.441568495999945 }, "TrainerController.advance": { "total": 2393.9390391859315, "count": 232203, "self": 4.399848814990037, "children": { "env_step": { "total": 1888.533511716008, "count": 232203, "self": 1582.0551956349454, "children": { "SubprocessEnvManager._take_step": { "total": 303.60490915294736, "count": 232203, "self": 15.656520873063073, "children": { "TorchPolicy.evaluate": { "total": 287.9483882798843, "count": 222940, "self": 71.67128815291017, "children": { "TorchPolicy.sample_actions": { "total": 216.27710012697412, "count": 222940, "self": 216.27710012697412 } } } } }, "workers": { "total": 2.8734069281151733, "count": 232203, "self": 0.0, "children": { "worker_root": { "total": 2399.327145317024, "count": 232203, "is_parallel": true, "self": 1102.724129625864, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0018555219999143446, "count": 1, "is_parallel": true, "self": 0.0003910009999117392, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014645210000026054, "count": 2, "is_parallel": true, "self": 0.0014645210000026054 } } }, "UnityEnvironment.step": { "total": 0.030903972999908547, "count": 1, "is_parallel": true, "self": 0.00034596499995132035, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00034969000000728556, "count": 1, "is_parallel": true, "self": 0.00034969000000728556 }, "communicator.exchange": { "total": 0.029338716999973258, "count": 1, "is_parallel": true, "self": 0.029338716999973258 }, "steps_from_proto": { "total": 0.0008696009999766829, "count": 1, "is_parallel": true, "self": 0.0003064850000100705, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005631159999666124, "count": 2, "is_parallel": true, "self": 0.0005631159999666124 } } } } } } }, "UnityEnvironment.step": { "total": 1296.6030156911602, "count": 232202, "is_parallel": true, "self": 36.29968849606348, "children": { "UnityEnvironment._generate_step_input": { "total": 82.79077629199173, "count": 232202, "is_parallel": true, "self": 82.79077629199173 }, "communicator.exchange": { "total": 1078.1693571060719, "count": 232202, "is_parallel": true, "self": 1078.1693571060719 }, "steps_from_proto": { "total": 99.343193797033, "count": 232202, "is_parallel": true, "self": 42.85255034110082, "children": { "_process_rank_one_or_two_observation": { "total": 56.49064345593217, "count": 464404, "is_parallel": true, "self": 56.49064345593217 } } } } } } } } } } }, "trainer_advance": { "total": 501.0056786549337, "count": 232203, "self": 6.754955714003927, "children": { "process_trajectory": { "total": 165.26270763992864, "count": 232203, "self": 164.77217340592836, "children": { "RLTrainer._checkpoint": { "total": 0.49053423400027896, "count": 4, "self": 0.49053423400027896 } } }, "_update_policy": { "total": 328.98801530100116, "count": 97, "self": 274.0570640029979, "children": { "TorchPPOOptimizer.update": { "total": 54.930951298003265, "count": 2910, "self": 54.930951298003265 } } } } } } }, "trainer_threads": { "total": 9.069999578059651e-07, "count": 1, "self": 9.069999578059651e-07 }, "TrainerController._save_models": { "total": 0.11361950099990281, "count": 1, "self": 0.0019937769998250587, "children": { "RLTrainer._checkpoint": { "total": 0.11162572400007775, "count": 1, "self": 0.11162572400007775 } } } } } } }