{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.0942000150680542, "min": 1.0942000150680542, "max": 2.8682949542999268, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 10447.421875, "min": 10447.421875, "max": 29374.208984375, "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": 12.525918960571289, "min": 0.5909805297851562, "max": 12.525918960571289, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2442.55419921875, "min": 114.65022277832031, "max": 2545.302734375, "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": 0.06227211903680262, "min": 0.06227211903680262, "max": 0.0801908915514907, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.24908847614721047, "min": 0.24908847614721047, "max": 0.36801745339671116, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.1931430067428771, "min": 0.12608044048515604, "max": 0.27375477774470464, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7725720269715084, "min": 0.5043217619406242, "max": 1.3687738887235232, "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": 24.40909090909091, "min": 3.75, "max": 24.90909090909091, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1074.0, "min": 165.0, "max": 1370.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 24.40909090909091, "min": 3.75, "max": 24.90909090909091, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1074.0, "min": 165.0, "max": 1370.0, "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": "1673456868", "python_version": "3.8.16 (default, Dec 7 2022, 01:12:13) \n[GCC 7.5.0]", "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": "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": "1673457335" }, "total": 467.61857581899994, "count": 1, "self": 0.4349125329998742, "children": { "run_training.setup": { "total": 0.11217131400007929, "count": 1, "self": 0.11217131400007929 }, "TrainerController.start_learning": { "total": 467.071491972, "count": 1, "self": 0.596926643009283, "children": { "TrainerController._reset_env": { "total": 7.475590416999921, "count": 1, "self": 7.475590416999921 }, "TrainerController.advance": { "total": 458.8694602429906, "count": 18201, "self": 0.32691252498466383, "children": { "env_step": { "total": 458.54254771800595, "count": 18201, "self": 303.20210405601085, "children": { "SubprocessEnvManager._take_step": { "total": 155.02560296799334, "count": 18201, "self": 1.5236862590054443, "children": { "TorchPolicy.evaluate": { "total": 153.5019167089879, "count": 18201, "self": 34.84279805298729, "children": { "TorchPolicy.sample_actions": { "total": 118.6591186560006, "count": 18201, "self": 118.6591186560006 } } } } }, "workers": { "total": 0.3148406940017594, "count": 18201, "self": 0.0, "children": { "worker_root": { "total": 465.6876764470021, "count": 18201, "is_parallel": true, "self": 221.0277791320035, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.006565117999912218, "count": 1, "is_parallel": true, "self": 0.0038448719999450987, "children": { "_process_rank_one_or_two_observation": { "total": 0.002720245999967119, "count": 10, "is_parallel": true, "self": 0.002720245999967119 } } }, "UnityEnvironment.step": { "total": 0.03262800699997115, "count": 1, "is_parallel": true, "self": 0.0005421719999958441, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00035759499996856903, "count": 1, "is_parallel": true, "self": 0.00035759499996856903 }, "communicator.exchange": { "total": 0.029715485999986413, "count": 1, "is_parallel": true, "self": 0.029715485999986413 }, "steps_from_proto": { "total": 0.0020127540000203226, "count": 1, "is_parallel": true, "self": 0.0004986720000488276, "children": { "_process_rank_one_or_two_observation": { "total": 0.001514081999971495, "count": 10, "is_parallel": true, "self": 0.001514081999971495 } } } } } } }, "UnityEnvironment.step": { "total": 244.6598973149986, "count": 18200, "is_parallel": true, "self": 9.315655299995683, "children": { "UnityEnvironment._generate_step_input": { "total": 5.313164259007863, "count": 18200, "is_parallel": true, "self": 5.313164259007863 }, "communicator.exchange": { "total": 197.1926399030025, "count": 18200, "is_parallel": true, "self": 197.1926399030025 }, "steps_from_proto": { "total": 32.83843785299257, "count": 18200, "is_parallel": true, "self": 7.22408198602534, "children": { "_process_rank_one_or_two_observation": { "total": 25.61435586696723, "count": 182000, "is_parallel": true, "self": 25.61435586696723 } } } } } } } } } } } } }, "trainer_threads": { "total": 4.7705000042697066e-05, "count": 1, "self": 4.7705000042697066e-05, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 455.65411804802466, "count": 377128, "is_parallel": true, "self": 10.105671874045925, "children": { "process_trajectory": { "total": 259.9929893109779, "count": 377128, "is_parallel": true, "self": 259.19807375297796, "children": { "RLTrainer._checkpoint": { "total": 0.794915557999957, "count": 4, "is_parallel": true, "self": 0.794915557999957 } } }, "_update_policy": { "total": 185.5554568630008, "count": 90, "is_parallel": true, "self": 48.50405841100337, "children": { "TorchPPOOptimizer.update": { "total": 137.05139845199744, "count": 4587, "is_parallel": true, "self": 137.05139845199744 } } } } } } } } }, "TrainerController._save_models": { "total": 0.12946696400013025, "count": 1, "self": 0.0008764300002894743, "children": { "RLTrainer._checkpoint": { "total": 0.12859053399984077, "count": 1, "self": 0.12859053399984077 } } } } } } }