{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.8107168078422546, "min": 0.7982370853424072, "max": 2.8597230911254883, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 7758.56005859375, "min": 7758.56005859375, "max": 29349.337890625, "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": 12.955330848693848, "min": 0.49590766429901123, "max": 12.955330848693848, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2526.28955078125, "min": 96.20608520507812, "max": 2642.47412109375, "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": 0.06533983295241128, "min": 0.05870542735213473, "max": 0.07862459737350982, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2613593318096451, "min": 0.24730187345595173, "max": 0.3931229868675491, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.199163460994468, "min": 0.12652212545485694, "max": 0.2986329855287776, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.796653843977872, "min": 0.5060885018194278, "max": 1.2634836853134865, "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": 25.931818181818183, "min": 3.727272727272727, "max": 25.931818181818183, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1141.0, "min": 164.0, "max": 1413.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.931818181818183, "min": 3.727272727272727, "max": 25.931818181818183, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1141.0, "min": 164.0, "max": 1413.0, "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": "1679250947", "python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \n[GCC 9.4.0]", "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": "1679251445" }, "total": 498.211284005, "count": 1, "self": 0.4357491819999382, "children": { "run_training.setup": { "total": 0.10549017400001048, "count": 1, "self": 0.10549017400001048 }, "TrainerController.start_learning": { "total": 497.67004464900003, "count": 1, "self": 0.6508035630095037, "children": { "TrainerController._reset_env": { "total": 10.238496202000022, "count": 1, "self": 10.238496202000022 }, "TrainerController.advance": { "total": 486.6439316449906, "count": 18204, "self": 0.33210549298667047, "children": { "env_step": { "total": 486.3118261520039, "count": 18204, "self": 350.1390331970025, "children": { "SubprocessEnvManager._take_step": { "total": 135.86348297899883, "count": 18204, "self": 2.3025231349932938, "children": { "TorchPolicy.evaluate": { "total": 133.56095984400554, "count": 18204, "self": 133.56095984400554 } } }, "workers": { "total": 0.3093099760025666, "count": 18204, "self": 0.0, "children": { "worker_root": { "total": 496.0334915700002, "count": 18204, "is_parallel": true, "self": 236.08835349500902, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005489699000008841, "count": 1, "is_parallel": true, "self": 0.004029495999986921, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014602030000219202, "count": 10, "is_parallel": true, "self": 0.0014602030000219202 } } }, "UnityEnvironment.step": { "total": 0.03591987700002619, "count": 1, "is_parallel": true, "self": 0.0006262669999159698, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00028740600004084627, "count": 1, "is_parallel": true, "self": 0.00028740600004084627 }, "communicator.exchange": { "total": 0.03309662400005209, "count": 1, "is_parallel": true, "self": 0.03309662400005209 }, "steps_from_proto": { "total": 0.0019095800000172858, "count": 1, "is_parallel": true, "self": 0.0003934870000534829, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015160929999638029, "count": 10, "is_parallel": true, "self": 0.0015160929999638029 } } } } } } }, "UnityEnvironment.step": { "total": 259.9451380749912, "count": 18203, "is_parallel": true, "self": 10.29743647998282, "children": { "UnityEnvironment._generate_step_input": { "total": 5.443198925008005, "count": 18203, "is_parallel": true, "self": 5.443198925008005 }, "communicator.exchange": { "total": 211.28585607599905, "count": 18203, "is_parallel": true, "self": 211.28585607599905 }, "steps_from_proto": { "total": 32.9186465940013, "count": 18203, "is_parallel": true, "self": 6.68266591797925, "children": { "_process_rank_one_or_two_observation": { "total": 26.235980676022052, "count": 182030, "is_parallel": true, "self": 26.235980676022052 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.0001456659999803378, "count": 1, "self": 0.0001456659999803378, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 482.98119474200837, "count": 432013, "is_parallel": true, "self": 11.154350977000945, "children": { "process_trajectory": { "total": 268.53354118300706, "count": 432013, "is_parallel": true, "self": 267.5819592740071, "children": { "RLTrainer._checkpoint": { "total": 0.9515819089999695, "count": 4, "is_parallel": true, "self": 0.9515819089999695 } } }, "_update_policy": { "total": 203.29330258200036, "count": 90, "is_parallel": true, "self": 73.54695058199701, "children": { "TorchPPOOptimizer.update": { "total": 129.74635200000336, "count": 4587, "is_parallel": true, "self": 129.74635200000336 } } } } } } } } }, "TrainerController._save_models": { "total": 0.13666757299995425, "count": 1, "self": 0.0009491089999755786, "children": { "RLTrainer._checkpoint": { "total": 0.13571846399997867, "count": 1, "self": 0.13571846399997867 } } } } } } }