{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4073126316070557, "min": 1.4073126316070557, "max": 1.4307005405426025, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 71174.8359375, "min": 66294.8125, "max": 75377.7578125, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 81.26885245901639, "min": 81.26885245901639, "max": 409.38524590163934, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49574.0, "min": 48817.0, "max": 50174.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999993.0, "min": 49317.0, "max": 1999993.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999993.0, "min": 49317.0, "max": 1999993.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.422433376312256, "min": 0.02333320491015911, "max": 2.5112802982330322, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1477.684326171875, "min": 2.823317766189575, "max": 1493.2392578125, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.7483108170696946, "min": 1.8085485976343312, "max": 4.017417683320887, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2286.4695984125137, "min": 218.83438031375408, "max": 2359.354767739773, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.7483108170696946, "min": 1.8085485976343312, "max": 4.017417683320887, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2286.4695984125137, "min": 218.83438031375408, "max": 2359.354767739773, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.01620290673066241, "min": 0.014207879180644846, "max": 0.021213491920692225, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.048608720191987226, "min": 0.02899081624527753, "max": 0.05680395646268152, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.05992192228635152, "min": 0.021966475641561883, "max": 0.0676796176367336, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.17976576685905457, "min": 0.04402433546880881, "max": 0.20303885291020077, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.3056488981500005e-06, "min": 3.3056488981500005e-06, "max": 0.0002953379265540249, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 9.916946694450002e-06, "min": 9.916946694450002e-06, "max": 0.00084386416871195, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10110184999999998, "min": 0.10110184999999998, "max": 0.19844597500000005, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.3033055499999999, "min": 0.207344, "max": 0.5812880500000002, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 6.498231500000002e-05, "min": 6.498231500000002e-05, "max": 0.0049224541525, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00019494694500000006, "min": 0.00019494694500000006, "max": 0.014066273694999997, "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": "1674963445", "python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \n[GCC 9.4.0]", "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": "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": "1674965588" }, "total": 2142.900144924, "count": 1, "self": 0.39659713399987595, "children": { "run_training.setup": { "total": 0.10377444900007049, "count": 1, "self": 0.10377444900007049 }, "TrainerController.start_learning": { "total": 2142.399773341, "count": 1, "self": 3.6642612699720303, "children": { "TrainerController._reset_env": { "total": 9.946715906000009, "count": 1, "self": 9.946715906000009 }, "TrainerController.advance": { "total": 2128.6819054670277, "count": 232573, "self": 4.038634869079942, "children": { "env_step": { "total": 1678.6634199930388, "count": 232573, "self": 1410.9302134732366, "children": { "SubprocessEnvManager._take_step": { "total": 265.2022251228826, "count": 232573, "self": 14.074211958874685, "children": { "TorchPolicy.evaluate": { "total": 251.12801316400794, "count": 223042, "self": 63.50124038491208, "children": { "TorchPolicy.sample_actions": { "total": 187.62677277909586, "count": 223042, "self": 187.62677277909586 } } } } }, "workers": { "total": 2.5309813969196284, "count": 232573, "self": 0.0, "children": { "worker_root": { "total": 2134.877249674918, "count": 232573, "is_parallel": true, "self": 969.6525419420584, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.003676735999988523, "count": 1, "is_parallel": true, "self": 0.0003635689998873204, "children": { "_process_rank_one_or_two_observation": { "total": 0.0033131670001012026, "count": 2, "is_parallel": true, "self": 0.0033131670001012026 } } }, "UnityEnvironment.step": { "total": 0.026575753999964036, "count": 1, "is_parallel": true, "self": 0.00027249100003245985, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00020895199997994496, "count": 1, "is_parallel": true, "self": 0.00020895199997994496 }, "communicator.exchange": { "total": 0.02521070399996006, "count": 1, "is_parallel": true, "self": 0.02521070399996006 }, "steps_from_proto": { "total": 0.0008836069999915708, "count": 1, "is_parallel": true, "self": 0.00024181800006317644, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006417889999283943, "count": 2, "is_parallel": true, "self": 0.0006417889999283943 } } } } } } }, "UnityEnvironment.step": { "total": 1165.2247077328595, "count": 232572, "is_parallel": true, "self": 33.47169618475459, "children": { "UnityEnvironment._generate_step_input": { "total": 73.26137300298228, "count": 232572, "is_parallel": true, "self": 73.26137300298228 }, "communicator.exchange": { "total": 969.5332721990196, "count": 232572, "is_parallel": true, "self": 969.5332721990196 }, "steps_from_proto": { "total": 88.95836634610293, "count": 232572, "is_parallel": true, "self": 36.699969083981046, "children": { "_process_rank_one_or_two_observation": { "total": 52.25839726212189, "count": 465144, "is_parallel": true, "self": 52.25839726212189 } } } } } } } } } } }, "trainer_advance": { "total": 445.97985060490896, "count": 232573, "self": 5.906112916011807, "children": { "process_trajectory": { "total": 140.90502452489693, "count": 232573, "self": 139.74755231289714, "children": { "RLTrainer._checkpoint": { "total": 1.1574722119997887, "count": 10, "self": 1.1574722119997887 } } }, "_update_policy": { "total": 299.1687131640002, "count": 97, "self": 246.76968617700481, "children": { "TorchPPOOptimizer.update": { "total": 52.39902698699541, "count": 2910, "self": 52.39902698699541 } } } } } } }, "trainer_threads": { "total": 9.82000074145617e-07, "count": 1, "self": 9.82000074145617e-07 }, "TrainerController._save_models": { "total": 0.10688971600029618, "count": 1, "self": 0.0027251780002188752, "children": { "RLTrainer._checkpoint": { "total": 0.1041645380000773, "count": 1, "self": 0.1041645380000773 } } } } } } }