{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.0563604831695557, "min": 1.0563604831695557, "max": 2.8580477237701416, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 10097.75, "min": 10097.75, "max": 29269.267578125, "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": 12.60400390625, "min": 0.5132509469985962, "max": 12.60400390625, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2457.78076171875, "min": 99.57068634033203, "max": 2527.25927734375, "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": 0.06433344205502448, "min": 0.06229348466713061, "max": 0.07575100726720777, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2573337682200979, "min": 0.24917393866852244, "max": 0.377388354380017, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.2162439647112407, "min": 0.1451800462616352, "max": 0.2934367781760646, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8649758588449628, "min": 0.5807201850465408, "max": 1.467183890880323, "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": 25.068181818181817, "min": 4.136363636363637, "max": 25.068181818181817, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1103.0, "min": 182.0, "max": 1367.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.068181818181817, "min": 4.136363636363637, "max": 25.068181818181817, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1103.0, "min": 182.0, "max": 1367.0, "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": "1693758490", "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/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics", "mlagents_version": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.11.0+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1693758986" }, "total": 495.174950922, "count": 1, "self": 0.738427062000028, "children": { "run_training.setup": { "total": 0.04022444099996392, "count": 1, "self": 0.04022444099996392 }, "TrainerController.start_learning": { "total": 494.396299419, "count": 1, "self": 0.5891258009954754, "children": { "TrainerController._reset_env": { "total": 3.9764636209999935, "count": 1, "self": 3.9764636209999935 }, "TrainerController.advance": { "total": 489.59245980900437, "count": 18210, "self": 0.30076954500225384, "children": { "env_step": { "total": 489.2916902640021, "count": 18210, "self": 356.4773580320207, "children": { "SubprocessEnvManager._take_step": { "total": 132.51293505497904, "count": 18210, "self": 1.8123175199742718, "children": { "TorchPolicy.evaluate": { "total": 130.70061753500477, "count": 18210, "self": 130.70061753500477 } } }, "workers": { "total": 0.3013971770024, "count": 18210, "self": 0.0, "children": { "worker_root": { "total": 492.52073100300436, "count": 18210, "is_parallel": true, "self": 230.0619742510088, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005761240999959227, "count": 1, "is_parallel": true, "self": 0.00426215799984675, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014990830001124777, "count": 10, "is_parallel": true, "self": 0.0014990830001124777 } } }, "UnityEnvironment.step": { "total": 0.036397772000100304, "count": 1, "is_parallel": true, "self": 0.0006033310002067083, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004623769999625438, "count": 1, "is_parallel": true, "self": 0.0004623769999625438 }, "communicator.exchange": { "total": 0.03318011099997875, "count": 1, "is_parallel": true, "self": 0.03318011099997875 }, "steps_from_proto": { "total": 0.0021519529999523, "count": 1, "is_parallel": true, "self": 0.0004740140000194515, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016779389999328487, "count": 10, "is_parallel": true, "self": 0.0016779389999328487 } } } } } } }, "UnityEnvironment.step": { "total": 262.45875675199557, "count": 18209, "is_parallel": true, "self": 10.91935654700967, "children": { "UnityEnvironment._generate_step_input": { "total": 5.713696213982303, "count": 18209, "is_parallel": true, "self": 5.713696213982303 }, "communicator.exchange": { "total": 206.39324489800538, "count": 18209, "is_parallel": true, "self": 206.39324489800538 }, "steps_from_proto": { "total": 39.432459092998215, "count": 18209, "is_parallel": true, "self": 7.204492932010453, "children": { "_process_rank_one_or_two_observation": { "total": 32.22796616098776, "count": 182090, "is_parallel": true, "self": 32.22796616098776 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00016238300008808437, "count": 1, "self": 0.00016238300008808437, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 485.6818867529811, "count": 468436, "is_parallel": true, "self": 10.447527992931214, "children": { "process_trajectory": { "total": 266.64672007504873, "count": 468436, "is_parallel": true, "self": 264.5338876550487, "children": { "RLTrainer._checkpoint": { "total": 2.112832420000018, "count": 4, "is_parallel": true, "self": 2.112832420000018 } } }, "_update_policy": { "total": 208.58763868500114, "count": 90, "is_parallel": true, "self": 82.31842025400158, "children": { "TorchPPOOptimizer.update": { "total": 126.26921843099956, "count": 4587, "is_parallel": true, "self": 126.26921843099956 } } } } } } } } }, "TrainerController._save_models": { "total": 0.23808780500007742, "count": 1, "self": 0.0010963889999402454, "children": { "RLTrainer._checkpoint": { "total": 0.23699141600013718, "count": 1, "self": 0.23699141600013718 } } } } } } }