{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9272059798240662, "min": 0.9200587272644043, "max": 2.866605520248413, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8863.162109375, "min": 8863.162109375, "max": 29451.50390625, "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": 12.781453132629395, "min": 0.21215924620628357, "max": 12.781453132629395, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2492.38330078125, "min": 41.15889358520508, "max": 2587.974853515625, "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": 0.06603064836538881, "min": 0.062333361273226286, "max": 0.07447813634587197, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.26412259346155526, "min": 0.24933344509290514, "max": 0.37239068172935985, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.1940956291030435, "min": 0.107623676897264, "max": 0.28307829030296383, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.776382516412174, "min": 0.430494707589056, "max": 1.3589069959616251, "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": 25.227272727272727, "min": 3.227272727272727, "max": 25.227272727272727, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1110.0, "min": 142.0, "max": 1380.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.227272727272727, "min": 3.227272727272727, "max": 25.227272727272727, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1110.0, "min": 142.0, "max": 1380.0, "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": "1681132715", "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": "1681133167" }, "total": 451.269502288, "count": 1, "self": 0.4355561479999892, "children": { "run_training.setup": { "total": 0.11611799299998893, "count": 1, "self": 0.11611799299998893 }, "TrainerController.start_learning": { "total": 450.71782814700003, "count": 1, "self": 0.5654220089935507, "children": { "TrainerController._reset_env": { "total": 3.8029033430000254, "count": 1, "self": 3.8029033430000254 }, "TrainerController.advance": { "total": 446.2172950900064, "count": 18202, "self": 0.2791107890039939, "children": { "env_step": { "total": 445.9381843010024, "count": 18202, "self": 327.1976788119985, "children": { "SubprocessEnvManager._take_step": { "total": 118.46668895000397, "count": 18202, "self": 1.879066501003365, "children": { "TorchPolicy.evaluate": { "total": 116.5876224490006, "count": 18202, "self": 116.5876224490006 } } }, "workers": { "total": 0.2738165389999381, "count": 18202, "self": 0.0, "children": { "worker_root": { "total": 449.25597041501186, "count": 18202, "is_parallel": true, "self": 207.48000606302264, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005491278000022248, "count": 1, "is_parallel": true, "self": 0.0038501430000792425, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016411349999430058, "count": 10, "is_parallel": true, "self": 0.0016411349999430058 } } }, "UnityEnvironment.step": { "total": 0.034066921999965416, "count": 1, "is_parallel": true, "self": 0.0005620670000325845, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003249399999845082, "count": 1, "is_parallel": true, "self": 0.0003249399999845082 }, "communicator.exchange": { "total": 0.031354300999964835, "count": 1, "is_parallel": true, "self": 0.031354300999964835 }, "steps_from_proto": { "total": 0.0018256139999834886, "count": 1, "is_parallel": true, "self": 0.0003894079999327005, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014362060000507881, "count": 10, "is_parallel": true, "self": 0.0014362060000507881 } } } } } } }, "UnityEnvironment.step": { "total": 241.77596435198922, "count": 18201, "is_parallel": true, "self": 9.867261946989345, "children": { "UnityEnvironment._generate_step_input": { "total": 5.320885933993452, "count": 18201, "is_parallel": true, "self": 5.320885933993452 }, "communicator.exchange": { "total": 195.42447291100268, "count": 18201, "is_parallel": true, "self": 195.42447291100268 }, "steps_from_proto": { "total": 31.16334356000374, "count": 18201, "is_parallel": true, "self": 6.248351599994692, "children": { "_process_rank_one_or_two_observation": { "total": 24.914991960009047, "count": 182010, "is_parallel": true, "self": 24.914991960009047 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.0001479159999462354, "count": 1, "self": 0.0001479159999462354, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 442.73268276701435, "count": 383280, "is_parallel": true, "self": 9.711899371036964, "children": { "process_trajectory": { "total": 242.88773031597782, "count": 383280, "is_parallel": true, "self": 241.43643787197772, "children": { "RLTrainer._checkpoint": { "total": 1.451292444000103, "count": 4, "is_parallel": true, "self": 1.451292444000103 } } }, "_update_policy": { "total": 190.13305307999957, "count": 90, "is_parallel": true, "self": 70.90683927499981, "children": { "TorchPPOOptimizer.update": { "total": 119.22621380499976, "count": 4584, "is_parallel": true, "self": 119.22621380499976 } } } } } } } } }, "TrainerController._save_models": { "total": 0.1320597890000954, "count": 1, "self": 0.0009716350000417151, "children": { "RLTrainer._checkpoint": { "total": 0.1310881540000537, "count": 1, "self": 0.1310881540000537 } } } } } } }