{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9555612802505493, "min": 0.936212956905365, "max": 2.877584218978882, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9123.69921875, "min": 9123.69921875, "max": 29564.30078125, "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": 12.15113639831543, "min": 0.37244194746017456, "max": 12.15113639831543, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2369.4716796875, "min": 72.25373840332031, "max": 2476.76953125, "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": 0.06519780296309595, "min": 0.06279386983392304, "max": 0.07301818262694368, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2607912118523838, "min": 0.2511754793356922, "max": 0.36509091313471836, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.191707533729427, "min": 0.11889657997480575, "max": 0.2851898031491859, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.766830134917708, "min": 0.475586319899223, "max": 1.4259490157459296, "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": 23.931818181818183, "min": 3.477272727272727, "max": 23.931818181818183, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1053.0, "min": 153.0, "max": 1307.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 23.931818181818183, "min": 3.477272727272727, "max": 23.931818181818183, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1053.0, "min": 153.0, "max": 1307.0, "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": "1689112603", "python_version": "3.10.12 (main, Jun 7 2023, 12:45:35) [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": "1689113068" }, "total": 464.9478828230001, "count": 1, "self": 0.43510287600008724, "children": { "run_training.setup": { "total": 0.041160321999996086, "count": 1, "self": 0.041160321999996086 }, "TrainerController.start_learning": { "total": 464.471619625, "count": 1, "self": 0.5489255670117927, "children": { "TrainerController._reset_env": { "total": 4.08380502600005, "count": 1, "self": 4.08380502600005 }, "TrainerController.advance": { "total": 459.69681944198817, "count": 18201, "self": 0.25222234597720217, "children": { "env_step": { "total": 459.44459709601097, "count": 18201, "self": 337.48616796501244, "children": { "SubprocessEnvManager._take_step": { "total": 121.70053765199475, "count": 18201, "self": 1.8650579739810382, "children": { "TorchPolicy.evaluate": { "total": 119.83547967801371, "count": 18201, "self": 119.83547967801371 } } }, "workers": { "total": 0.2578914790037743, "count": 18201, "self": 0.0, "children": { "worker_root": { "total": 462.85615569500396, "count": 18201, "is_parallel": true, "self": 218.62783515600108, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005298880999930589, "count": 1, "is_parallel": true, "self": 0.0036629259999472197, "children": { "_process_rank_one_or_two_observation": { "total": 0.001635954999983369, "count": 10, "is_parallel": true, "self": 0.001635954999983369 } } }, "UnityEnvironment.step": { "total": 0.03508686900011071, "count": 1, "is_parallel": true, "self": 0.0006429830001479786, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003344539999261542, "count": 1, "is_parallel": true, "self": 0.0003344539999261542 }, "communicator.exchange": { "total": 0.03200260000005528, "count": 1, "is_parallel": true, "self": 0.03200260000005528 }, "steps_from_proto": { "total": 0.0021068319999812957, "count": 1, "is_parallel": true, "self": 0.0003583020001087789, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017485299998725168, "count": 10, "is_parallel": true, "self": 0.0017485299998725168 } } } } } } }, "UnityEnvironment.step": { "total": 244.22832053900288, "count": 18200, "is_parallel": true, "self": 10.225537699014694, "children": { "UnityEnvironment._generate_step_input": { "total": 5.07230876299343, "count": 18200, "is_parallel": true, "self": 5.07230876299343 }, "communicator.exchange": { "total": 193.84522547299912, "count": 18200, "is_parallel": true, "self": 193.84522547299912 }, "steps_from_proto": { "total": 35.08524860399564, "count": 18200, "is_parallel": true, "self": 6.351173738004945, "children": { "_process_rank_one_or_two_observation": { "total": 28.734074865990692, "count": 182000, "is_parallel": true, "self": 28.734074865990692 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00015494699994178518, "count": 1, "self": 0.00015494699994178518, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 456.152562381043, "count": 442630, "is_parallel": true, "self": 9.702451761070847, "children": { "process_trajectory": { "total": 247.9258669009722, "count": 442630, "is_parallel": true, "self": 246.83381302397208, "children": { "RLTrainer._checkpoint": { "total": 1.0920538770001258, "count": 4, "is_parallel": true, "self": 1.0920538770001258 } } }, "_update_policy": { "total": 198.52424371899997, "count": 90, "is_parallel": true, "self": 80.11556589400027, "children": { "TorchPPOOptimizer.update": { "total": 118.4086778249997, "count": 4587, "is_parallel": true, "self": 118.4086778249997 } } } } } } } } }, "TrainerController._save_models": { "total": 0.14191464300006373, "count": 1, "self": 0.0008432220000713642, "children": { "RLTrainer._checkpoint": { "total": 0.14107142099999237, "count": 1, "self": 0.14107142099999237 } } } } } } }