{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.0143705606460571, "min": 1.0143705606460571, "max": 2.8694255352020264, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9685.2099609375, "min": 9685.2099609375, "max": 29575.169921875, "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": 12.360451698303223, "min": 0.3526623845100403, "max": 12.360451698303223, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2410.2880859375, "min": 68.41650390625, "max": 2476.49267578125, "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": 0.06354671712295956, "min": 0.060822526446238895, "max": 0.07498475004840122, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.25418686849183825, "min": 0.24329010578495558, "max": 0.3749237502420061, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.2024862764804971, "min": 0.11789987904051612, "max": 0.28095434043629497, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8099451059219884, "min": 0.47159951616206447, "max": 1.2733387120214164, "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": 24.795454545454547, "min": 3.0681818181818183, "max": 24.795454545454547, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1091.0, "min": 135.0, "max": 1331.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 24.795454545454547, "min": 3.0681818181818183, "max": 24.795454545454547, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1091.0, "min": 135.0, "max": 1331.0, "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": "1677661058", "python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \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": "0.29.0.dev0", "mlagents_envs_version": "0.29.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.8.1+cu102", "numpy_version": "1.22.4", "end_time_seconds": "1677661584" }, "total": 525.790381489, "count": 1, "self": 0.4397860159998572, "children": { "run_training.setup": { "total": 0.12009269800000766, "count": 1, "self": 0.12009269800000766 }, "TrainerController.start_learning": { "total": 525.2305027750001, "count": 1, "self": 0.6851466210046055, "children": { "TrainerController._reset_env": { "total": 9.650623507999967, "count": 1, "self": 9.650623507999967 }, "TrainerController.advance": { "total": 514.7575166979955, "count": 18201, "self": 0.3603878399948144, "children": { "env_step": { "total": 514.3971288580007, "count": 18201, "self": 354.9093732620004, "children": { "SubprocessEnvManager._take_step": { "total": 159.15650669299987, "count": 18201, "self": 1.7762142430059953, "children": { "TorchPolicy.evaluate": { "total": 157.38029244999387, "count": 18201, "self": 36.58319647698801, "children": { "TorchPolicy.sample_actions": { "total": 120.79709597300587, "count": 18201, "self": 120.79709597300587 } } } } }, "workers": { "total": 0.33124890300041443, "count": 18201, "self": 0.0, "children": { "worker_root": { "total": 523.2946779239874, "count": 18201, "is_parallel": true, "self": 252.6463102589878, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.006789581000020917, "count": 1, "is_parallel": true, "self": 0.003735501999983626, "children": { "_process_rank_one_or_two_observation": { "total": 0.003054079000037291, "count": 10, "is_parallel": true, "self": 0.003054079000037291 } } }, "UnityEnvironment.step": { "total": 0.054743571999949836, "count": 1, "is_parallel": true, "self": 0.0006568729999685274, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00044318700003032063, "count": 1, "is_parallel": true, "self": 0.00044318700003032063 }, "communicator.exchange": { "total": 0.0514214159999824, "count": 1, "is_parallel": true, "self": 0.0514214159999824 }, "steps_from_proto": { "total": 0.0022220959999685874, "count": 1, "is_parallel": true, "self": 0.0005014019999975972, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017206939999709903, "count": 10, "is_parallel": true, "self": 0.0017206939999709903 } } } } } } }, "UnityEnvironment.step": { "total": 270.64836766499957, "count": 18200, "is_parallel": true, "self": 10.747688306012492, "children": { "UnityEnvironment._generate_step_input": { "total": 6.0107953729979045, "count": 18200, "is_parallel": true, "self": 6.0107953729979045 }, "communicator.exchange": { "total": 217.3708586159982, "count": 18200, "is_parallel": true, "self": 217.3708586159982 }, "steps_from_proto": { "total": 36.51902536999097, "count": 18200, "is_parallel": true, "self": 8.4144238510342, "children": { "_process_rank_one_or_two_observation": { "total": 28.10460151895677, "count": 182000, "is_parallel": true, "self": 28.10460151895677 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00016791500002000248, "count": 1, "self": 0.00016791500002000248, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 510.645752482986, "count": 443046, "is_parallel": true, "self": 12.082190306022142, "children": { "process_trajectory": { "total": 291.2602027829633, "count": 443046, "is_parallel": true, "self": 290.0460034139632, "children": { "RLTrainer._checkpoint": { "total": 1.2141993690000845, "count": 4, "is_parallel": true, "self": 1.2141993690000845 } } }, "_update_policy": { "total": 207.30335939400055, "count": 90, "is_parallel": true, "self": 73.46875778500078, "children": { "TorchPPOOptimizer.update": { "total": 133.83460160899978, "count": 4587, "is_parallel": true, "self": 133.83460160899978 } } } } } } } } }, "TrainerController._save_models": { "total": 0.13704803300004187, "count": 1, "self": 0.0009272310001051665, "children": { "RLTrainer._checkpoint": { "total": 0.1361208019999367, "count": 1, "self": 0.1361208019999367 } } } } } } }