{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.8328796029090881, "min": 0.8328796029090881, "max": 2.858264207839966, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 7970.65771484375, "min": 7970.65771484375, "max": 29240.04296875, "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": 12.516498565673828, "min": 0.36898088455200195, "max": 12.579795837402344, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2440.71728515625, "min": 71.58229064941406, "max": 2566.2783203125, "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": 0.07502772115563572, "min": 0.06310748045212658, "max": 0.07502772115563572, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.3001108846225429, "min": 0.2524299218085063, "max": 0.37427813455110925, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.185929895762135, "min": 0.11939776109705003, "max": 0.28565592415192553, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.74371958304854, "min": 0.4775910443882001, "max": 1.4282796207596276, "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": 24.318181818181817, "min": 3.227272727272727, "max": 24.78181818181818, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1070.0, "min": 142.0, "max": 1363.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 24.318181818181817, "min": 3.227272727272727, "max": 24.78181818181818, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1070.0, "min": 142.0, "max": 1363.0, "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": "1696105621", "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": "1696106100" }, "total": 478.72680000800005, "count": 1, "self": 0.6883210390003569, "children": { "run_training.setup": { "total": 0.047849144999872806, "count": 1, "self": 0.047849144999872806 }, "TrainerController.start_learning": { "total": 477.9906298239998, "count": 1, "self": 0.5758805129992197, "children": { "TrainerController._reset_env": { "total": 4.175138771999855, "count": 1, "self": 4.175138771999855 }, "TrainerController.advance": { "total": 473.0021616750007, "count": 18219, "self": 0.27869493299976966, "children": { "env_step": { "total": 472.72346674200094, "count": 18219, "self": 345.5334004509982, "children": { "SubprocessEnvManager._take_step": { "total": 126.90899951600863, "count": 18219, "self": 1.7514701409913869, "children": { "TorchPolicy.evaluate": { "total": 125.15752937501725, "count": 18219, "self": 125.15752937501725 } } }, "workers": { "total": 0.2810667749940876, "count": 18219, "self": 0.0, "children": { "worker_root": { "total": 476.33685771400997, "count": 18219, "is_parallel": true, "self": 225.28111237900612, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005625516000009156, "count": 1, "is_parallel": true, "self": 0.0032357879995288386, "children": { "_process_rank_one_or_two_observation": { "total": 0.002389728000480318, "count": 10, "is_parallel": true, "self": 0.002389728000480318 } } }, "UnityEnvironment.step": { "total": 0.04729122100002314, "count": 1, "is_parallel": true, "self": 0.0006442199999128206, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00033434900001338974, "count": 1, "is_parallel": true, "self": 0.00033434900001338974 }, "communicator.exchange": { "total": 0.04317632600009347, "count": 1, "is_parallel": true, "self": 0.04317632600009347 }, "steps_from_proto": { "total": 0.0031363260000034643, "count": 1, "is_parallel": true, "self": 0.00038658799962831836, "children": { "_process_rank_one_or_two_observation": { "total": 0.002749738000375146, "count": 10, "is_parallel": true, "self": 0.002749738000375146 } } } } } } }, "UnityEnvironment.step": { "total": 251.05574533500385, "count": 18218, "is_parallel": true, "self": 10.611067982013083, "children": { "UnityEnvironment._generate_step_input": { "total": 5.4200618019851845, "count": 18218, "is_parallel": true, "self": 5.4200618019851845 }, "communicator.exchange": { "total": 198.6868929230102, "count": 18218, "is_parallel": true, "self": 198.6868929230102 }, "steps_from_proto": { "total": 36.33772262799539, "count": 18218, "is_parallel": true, "self": 6.627081134016407, "children": { "_process_rank_one_or_two_observation": { "total": 29.710641493978983, "count": 182180, "is_parallel": true, "self": 29.710641493978983 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00014497699999083125, "count": 1, "self": 0.00014497699999083125, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 469.35612516808646, "count": 446151, "is_parallel": true, "self": 10.012422029084746, "children": { "process_trajectory": { "total": 256.04425948600056, "count": 446151, "is_parallel": true, "self": 254.3792064800009, "children": { "RLTrainer._checkpoint": { "total": 1.6650530059996527, "count": 4, "is_parallel": true, "self": 1.6650530059996527 } } }, "_update_policy": { "total": 203.29944365300116, "count": 90, "is_parallel": true, "self": 82.8582012269942, "children": { "TorchPPOOptimizer.update": { "total": 120.44124242600697, "count": 4587, "is_parallel": true, "self": 120.44124242600697 } } } } } } } } }, "TrainerController._save_models": { "total": 0.23730388700005278, "count": 1, "self": 0.001159647000122277, "children": { "RLTrainer._checkpoint": { "total": 0.2361442399999305, "count": 1, "self": 0.2361442399999305 } } } } } } }