{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4043161869049072, "min": 1.4043161869049072, "max": 1.4293899536132812, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 70225.640625, "min": 68646.609375, "max": 77469.7890625, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 93.70208728652752, "min": 78.72611464968153, "max": 402.88709677419354, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49381.0, "min": 49201.0, "max": 50264.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999694.0, "min": 49344.0, "max": 1999694.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999694.0, "min": 49344.0, "max": 1999694.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.3873391151428223, "min": 0.17323459684848785, "max": 2.5321223735809326, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1258.127685546875, "min": 21.3078556060791, "max": 1540.7625732421875, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.5084869440864113, "min": 1.9187798832005603, "max": 4.066450367543509, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 1848.9726195335388, "min": 236.0099256336689, "max": 2401.586157441139, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.5084869440864113, "min": 1.9187798832005603, "max": 4.066450367543509, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 1848.9726195335388, "min": 236.0099256336689, "max": 2401.586157441139, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.01673149796552025, "min": 0.013618242766662863, "max": 0.02033802231477845, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.05019449389656074, "min": 0.029838838606277326, "max": 0.05519322702117885, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.04710768395000034, "min": 0.02154293234149615, "max": 0.06202678922563791, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.14132305185000102, "min": 0.0430858646829923, "max": 0.1759417314082384, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.3894488702166678e-06, "min": 3.3894488702166678e-06, "max": 0.00029532322655892495, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.0168346610650004e-05, "min": 1.0168346610650004e-05, "max": 0.0008441026686324498, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10112978333333338, "min": 0.10112978333333338, "max": 0.198441075, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.3033893500000001, "min": 0.20751895000000006, "max": 0.5813675500000002, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 6.637618833333336e-05, "min": 6.637618833333336e-05, "max": 0.004922209642500001, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.0001991285650000001, "min": 0.0001991285650000001, "max": 0.014070240745, "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": "1709780159", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "command_line_arguments": "/home/dl/miniconda3/envs/huggydog/bin/mlagents-learn ./config/ppo/Huggy.yaml --env=./ml-agents/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": "2.2.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1709782039" }, "total": 1879.6682417130069, "count": 1, "self": 0.37042218299757224, "children": { "run_training.setup": { "total": 0.014723974003572948, "count": 1, "self": 0.014723974003572948 }, "TrainerController.start_learning": { "total": 1879.2830955560057, "count": 1, "self": 2.54108033022203, "children": { "TrainerController._reset_env": { "total": 1.8699685909959953, "count": 1, "self": 1.8699685909959953 }, "TrainerController.advance": { "total": 1874.7994812977995, "count": 232779, "self": 2.558264800449251, "children": { "env_step": { "total": 1550.595442928592, "count": 232779, "self": 1337.2712454085413, "children": { "SubprocessEnvManager._take_step": { "total": 211.66019222827163, "count": 232779, "self": 10.874052669401863, "children": { "TorchPolicy.evaluate": { "total": 200.78613955886976, "count": 223052, "self": 200.78613955886976 } } }, "workers": { "total": 1.6640052917791763, "count": 232779, "self": 0.0, "children": { "worker_root": { "total": 1872.5450671652943, "count": 232779, "is_parallel": true, "self": 768.6756163278042, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0006918449944350868, "count": 1, "is_parallel": true, "self": 0.00016549299471080303, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005263519997242838, "count": 2, "is_parallel": true, "self": 0.0005263519997242838 } } }, "UnityEnvironment.step": { "total": 0.026213526012725197, "count": 1, "is_parallel": true, "self": 0.0004118140059290454, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00025094300508499146, "count": 1, "is_parallel": true, "self": 0.00025094300508499146 }, "communicator.exchange": { "total": 0.02152034200844355, "count": 1, "is_parallel": true, "self": 0.02152034200844355 }, "steps_from_proto": { "total": 0.004030426993267611, "count": 1, "is_parallel": true, "self": 0.00025552000442985445, "children": { "_process_rank_one_or_two_observation": { "total": 0.003774906988837756, "count": 2, "is_parallel": true, "self": 0.003774906988837756 } } } } } } }, "UnityEnvironment.step": { "total": 1103.8694508374901, "count": 232778, "is_parallel": true, "self": 32.88515648544126, "children": { "UnityEnvironment._generate_step_input": { "total": 67.98563811712665, "count": 232778, "is_parallel": true, "self": 67.98563811712665 }, "communicator.exchange": { "total": 926.8408511440066, "count": 232778, "is_parallel": true, "self": 926.8408511440066 }, "steps_from_proto": { "total": 76.15780509091564, "count": 232778, "is_parallel": true, "self": 28.292735317416373, "children": { "_process_rank_one_or_two_observation": { "total": 47.86506977349927, "count": 465556, "is_parallel": true, "self": 47.86506977349927 } } } } } } } } } } }, "trainer_advance": { "total": 321.64577356875816, "count": 232779, "self": 4.687268801877508, "children": { "process_trajectory": { "total": 106.18434272368904, "count": 232779, "self": 105.32958651668741, "children": { "RLTrainer._checkpoint": { "total": 0.8547562070016284, "count": 10, "self": 0.8547562070016284 } } }, "_update_policy": { "total": 210.7741620431916, "count": 97, "self": 166.00863801331434, "children": { "TorchPPOOptimizer.update": { "total": 44.76552402987727, "count": 2910, "self": 44.76552402987727 } } } } } } }, "trainer_threads": { "total": 6.729969754815102e-07, "count": 1, "self": 6.729969754815102e-07 }, "TrainerController._save_models": { "total": 0.07256466399121564, "count": 1, "self": 0.0012088859948562458, "children": { "RLTrainer._checkpoint": { "total": 0.07135577799635939, "count": 1, "self": 0.07135577799635939 } } } } } } }