{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.7121079564094543, "min": 0.7121079564094543, "max": 2.8595473766326904, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 6807.0400390625, "min": 6807.0400390625, "max": 29284.625, "count": 20 }, "SnowballTarget.Step.mean": { "value": 199984.0, "min": 9952.0, "max": 199984.0, "count": 20 }, "SnowballTarget.Step.sum": { "value": 199984.0, "min": 9952.0, "max": 199984.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 12.908916473388672, "min": 0.31119251251220703, "max": 12.908916473388672, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2517.23876953125, "min": 60.3713493347168, "max": 2612.2099609375, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 8756.0, "min": 8756.0, "max": 10945.0, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06451627590942344, "min": 0.06319203467566839, "max": 0.07642889091943039, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.25806510363769375, "min": 0.2548535442905382, "max": 0.38214445459715196, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.18225170708462304, "min": 0.0995421836394634, "max": 0.27192777322203504, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7290068283384922, "min": 0.3981687345578536, "max": 1.3062093678642723, "count": 20 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 8.082097306000005e-06, "min": 8.082097306000005e-06, "max": 0.000291882002706, "count": 20 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 3.232838922400002e-05, "min": 3.232838922400002e-05, "max": 0.00138516003828, "count": 20 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10269400000000001, "min": 0.10269400000000001, "max": 0.19729400000000002, "count": 20 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.41077600000000003, "min": 0.41077600000000003, "max": 0.96172, "count": 20 }, "SnowballTarget.Policy.Beta.mean": { "value": 0.0001444306000000001, "min": 0.0001444306000000001, "max": 0.0048649706, "count": 20 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.0005777224000000004, "min": 0.0005777224000000004, "max": 0.023089828, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 25.181818181818183, "min": 3.090909090909091, "max": 25.527272727272727, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1108.0, "min": 136.0, "max": 1404.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.181818181818183, "min": 3.090909090909091, "max": 25.527272727272727, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1108.0, "min": 136.0, "max": 1404.0, "count": 20 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 20 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 20 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1714514172", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --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": "1714514609" }, "total": 436.945572806, "count": 1, "self": 0.4409558139998353, "children": { "run_training.setup": { "total": 0.056290211000032286, "count": 1, "self": 0.056290211000032286 }, "TrainerController.start_learning": { "total": 436.4483267810001, "count": 1, "self": 0.5465178749857387, "children": { "TrainerController._reset_env": { "total": 3.339909051999939, "count": 1, "self": 3.339909051999939 }, "TrainerController.advance": { "total": 432.4717775510146, "count": 18200, "self": 0.24559585901465653, "children": { "env_step": { "total": 432.22618169199995, "count": 18200, "self": 277.5202569279892, "children": { "SubprocessEnvManager._take_step": { "total": 154.43693335100295, "count": 18200, "self": 1.4200033949999806, "children": { "TorchPolicy.evaluate": { "total": 153.01692995600297, "count": 18200, "self": 153.01692995600297 } } }, "workers": { "total": 0.26899141300782503, "count": 18200, "self": 0.0, "children": { "worker_root": { "total": 435.34474181300084, "count": 18200, "is_parallel": true, "self": 219.6483815029934, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.006969857999933993, "count": 1, "is_parallel": true, "self": 0.005478620999952, "children": { "_process_rank_one_or_two_observation": { "total": 0.001491236999981993, "count": 10, "is_parallel": true, "self": 0.001491236999981993 } } }, "UnityEnvironment.step": { "total": 0.06820456999992075, "count": 1, "is_parallel": true, "self": 0.0007026789999144967, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00045595699998557393, "count": 1, "is_parallel": true, "self": 0.00045595699998557393 }, "communicator.exchange": { "total": 0.0648353760000191, "count": 1, "is_parallel": true, "self": 0.0648353760000191 }, "steps_from_proto": { "total": 0.0022105580000015834, "count": 1, "is_parallel": true, "self": 0.0004020720000426081, "children": { "_process_rank_one_or_two_observation": { "total": 0.0018084859999589753, "count": 10, "is_parallel": true, "self": 0.0018084859999589753 } } } } } } }, "UnityEnvironment.step": { "total": 215.69636031000744, "count": 18199, "is_parallel": true, "self": 9.995821491021843, "children": { "UnityEnvironment._generate_step_input": { "total": 5.297347207001053, "count": 18199, "is_parallel": true, "self": 5.297347207001053 }, "communicator.exchange": { "total": 166.7636435019873, "count": 18199, "is_parallel": true, "self": 166.7636435019873 }, "steps_from_proto": { "total": 33.639548109997236, "count": 18199, "is_parallel": true, "self": 6.2327170149742415, "children": { "_process_rank_one_or_two_observation": { "total": 27.406831095022994, "count": 181990, "is_parallel": true, "self": 27.406831095022994 } } } } } } } } } } } } }, "trainer_threads": { "total": 3.69069998669147e-05, "count": 1, "self": 3.69069998669147e-05, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 426.98673489203816, "count": 666921, "is_parallel": true, "self": 13.850078429007908, "children": { "process_trajectory": { "total": 236.46473139302987, "count": 666921, "is_parallel": true, "self": 235.89841313002978, "children": { "RLTrainer._checkpoint": { "total": 0.5663182630000847, "count": 4, "is_parallel": true, "self": 0.5663182630000847 } } }, "_update_policy": { "total": 176.67192507000038, "count": 90, "is_parallel": true, "self": 50.882927757011544, "children": { "TorchPPOOptimizer.update": { "total": 125.78899731298884, "count": 4587, "is_parallel": true, "self": 125.78899731298884 } } } } } } } } }, "TrainerController._save_models": { "total": 0.09008539599994947, "count": 1, "self": 0.0009514630000921898, "children": { "RLTrainer._checkpoint": { "total": 0.08913393299985728, "count": 1, "self": 0.08913393299985728 } } } } } } }