{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 0.6611718535423279, "min": 0.6611718535423279, "max": 1.414249062538147, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 33438.10546875, "min": 32083.75, "max": 75881.53125, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 133.9946380697051, "min": 118.67061611374407, "max": 389.2692307692308, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49980.0, "min": 48956.0, "max": 50605.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999830.0, "min": 49985.0, "max": 1999830.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999830.0, "min": 49985.0, "max": 1999830.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.335261344909668, "min": 0.06250770390033722, "max": 2.4759836196899414, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 871.052490234375, "min": 8.063493728637695, "max": 990.1101684570312, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.4644244797427914, "min": 1.870309018118437, "max": 3.791414874144877, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 1292.2303309440613, "min": 241.26986333727837, "max": 1512.8803631067276, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.4644244797427914, "min": 1.870309018118437, "max": 3.791414874144877, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 1292.2303309440613, "min": 241.26986333727837, "max": 1512.8803631067276, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.016771361622956345, "min": 0.016771361622956345, "max": 0.02476167705882593, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.03354272324591269, "min": 0.03354272324591269, "max": 0.07270653479799269, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.03513679567724466, "min": 0.014274755710115036, "max": 0.03513679567724466, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.07027359135448932, "min": 0.028549511420230073, "max": 0.08822762042284012, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 4.412723529124998e-06, "min": 4.412723529124998e-06, "max": 0.00029535555154815, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 8.825447058249995e-06, "min": 8.825447058249995e-06, "max": 0.0008442054185981997, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.101470875, "min": 0.101470875, "max": 0.19845184999999999, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.20294175, "min": 0.20294175, "max": 0.5814018000000001, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 8.339666249999995e-05, "min": 8.339666249999995e-05, "max": 0.004922747315, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.0001667933249999999, "min": 0.0001667933249999999, "max": 0.01407194982, "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": "1696548538", "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [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=Huggy --no-graphics", "mlagents_version": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.0.1+cu118", "numpy_version": "1.21.2", "end_time_seconds": "1696552725" }, "total": 4187.225689193, "count": 1, "self": 0.5403633960004299, "children": { "run_training.setup": { "total": 0.04859191500008819, "count": 1, "self": 0.04859191500008819 }, "TrainerController.start_learning": { "total": 4186.636733882, "count": 1, "self": 4.546494890983013, "children": { "TrainerController._reset_env": { "total": 8.983315911999966, "count": 1, "self": 8.983315911999966 }, "TrainerController.advance": { "total": 4172.995693837017, "count": 229412, "self": 4.980458286888279, "children": { "env_step": { "total": 1953.631862462073, "count": 229412, "self": 1612.9687101210293, "children": { "SubprocessEnvManager._take_step": { "total": 337.74099276405104, "count": 229412, "self": 17.68899038797929, "children": { "TorchPolicy.evaluate": { "total": 320.05200237607175, "count": 222896, "self": 320.05200237607175 } } }, "workers": { "total": 2.922159576992726, "count": 229412, "self": 0.0, "children": { "worker_root": { "total": 4179.223138076979, "count": 229412, "is_parallel": true, "self": 2865.9997662308724, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0007924369999727787, "count": 1, "is_parallel": true, "self": 0.00021984399995744752, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005725930000153312, "count": 2, "is_parallel": true, "self": 0.0005725930000153312 } } }, "UnityEnvironment.step": { "total": 0.02914684099994247, "count": 1, "is_parallel": true, "self": 0.0003064859999994951, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00021784999989904463, "count": 1, "is_parallel": true, "self": 0.00021784999989904463 }, "communicator.exchange": { "total": 0.027862622000043302, "count": 1, "is_parallel": true, "self": 0.027862622000043302 }, "steps_from_proto": { "total": 0.0007598830000006274, "count": 1, "is_parallel": true, "self": 0.00021704299990688014, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005428400000937472, "count": 2, "is_parallel": true, "self": 0.0005428400000937472 } } } } } } }, "UnityEnvironment.step": { "total": 1313.2233718461064, "count": 229411, "is_parallel": true, "self": 40.972286865023534, "children": { "UnityEnvironment._generate_step_input": { "total": 85.9271397639917, "count": 229411, "is_parallel": true, "self": 85.9271397639917 }, "communicator.exchange": { "total": 1084.7901347529298, "count": 229411, "is_parallel": true, "self": 1084.7901347529298 }, "steps_from_proto": { "total": 101.53381046416155, "count": 229411, "is_parallel": true, "self": 36.83025868320601, "children": { "_process_rank_one_or_two_observation": { "total": 64.70355178095554, "count": 458822, "is_parallel": true, "self": 64.70355178095554 } } } } } } } } } } }, "trainer_advance": { "total": 2214.3833730880556, "count": 229412, "self": 6.783746812111076, "children": { "process_trajectory": { "total": 140.70585371694472, "count": 229412, "self": 139.4431161229453, "children": { "RLTrainer._checkpoint": { "total": 1.262737593999418, "count": 10, "self": 1.262737593999418 } } }, "_update_policy": { "total": 2066.893772559, "count": 96, "self": 1753.7097748639985, "children": { "TorchPPOOptimizer.update": { "total": 313.1839976950015, "count": 14400, "self": 313.1839976950015 } } } } } } }, "trainer_threads": { "total": 1.3669996405951679e-06, "count": 1, "self": 1.3669996405951679e-06 }, "TrainerController._save_models": { "total": 0.11122787500062259, "count": 1, "self": 0.001890457000627066, "children": { "RLTrainer._checkpoint": { "total": 0.10933741799999552, "count": 1, "self": 0.10933741799999552 } } } } } } }