{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.7429056167602539, "min": 0.7429056167602539, "max": 2.857834815979004, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 7093.2626953125, "min": 7093.2626953125, "max": 29267.0859375, "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": 12.60680866241455, "min": 0.43271055817604065, "max": 12.60680866241455, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2458.32763671875, "min": 83.94584655761719, "max": 2540.91259765625, "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": 0.06859982424922398, "min": 0.06195274367036844, "max": 0.07545998047518486, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2743992969968959, "min": 0.24781097468147376, "max": 0.3772999023759243, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.1831049217166854, "min": 0.13713349790001908, "max": 0.2746544948541651, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7324196868667416, "min": 0.5485339916000763, "max": 1.3092656100497528, "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": 3.659090909090909, "max": 25.227272727272727, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1110.0, "min": 161.0, "max": 1375.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.227272727272727, "min": 3.659090909090909, "max": 25.227272727272727, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1110.0, "min": 161.0, "max": 1375.0, "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": "1707012317", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [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": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.2.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1707012797" }, "total": 480.4348245599999, "count": 1, "self": 0.4415100579999489, "children": { "run_training.setup": { "total": 0.051070225999865215, "count": 1, "self": 0.051070225999865215 }, "TrainerController.start_learning": { "total": 479.9422442760001, "count": 1, "self": 0.6455162150214164, "children": { "TrainerController._reset_env": { "total": 3.3080211229998895, "count": 1, "self": 3.3080211229998895 }, "TrainerController.advance": { "total": 475.89028578997886, "count": 18200, "self": 0.3075488239851438, "children": { "env_step": { "total": 475.5827369659937, "count": 18200, "self": 309.5878968089514, "children": { "SubprocessEnvManager._take_step": { "total": 165.6829203920156, "count": 18200, "self": 1.5804220500044721, "children": { "TorchPolicy.evaluate": { "total": 164.10249834201113, "count": 18200, "self": 164.10249834201113 } } }, "workers": { "total": 0.31191976502668695, "count": 18200, "self": 0.0, "children": { "worker_root": { "total": 478.7343226300254, "count": 18200, "is_parallel": true, "self": 235.3100015580785, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005520285999864427, "count": 1, "is_parallel": true, "self": 0.0038077490003161074, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017125369995483197, "count": 10, "is_parallel": true, "self": 0.0017125369995483197 } } }, "UnityEnvironment.step": { "total": 0.040186260999689694, "count": 1, "is_parallel": true, "self": 0.0007031439995444089, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004431750003277557, "count": 1, "is_parallel": true, "self": 0.0004431750003277557 }, "communicator.exchange": { "total": 0.036663396999756515, "count": 1, "is_parallel": true, "self": 0.036663396999756515 }, "steps_from_proto": { "total": 0.0023765450000610144, "count": 1, "is_parallel": true, "self": 0.0004499490009948204, "children": { "_process_rank_one_or_two_observation": { "total": 0.001926595999066194, "count": 10, "is_parallel": true, "self": 0.001926595999066194 } } } } } } }, "UnityEnvironment.step": { "total": 243.4243210719469, "count": 18199, "is_parallel": true, "self": 11.454262680918873, "children": { "UnityEnvironment._generate_step_input": { "total": 5.8948589639858255, "count": 18199, "is_parallel": true, "self": 5.8948589639858255 }, "communicator.exchange": { "total": 188.33706712399817, "count": 18199, "is_parallel": true, "self": 188.33706712399817 }, "steps_from_proto": { "total": 37.73813230304404, "count": 18199, "is_parallel": true, "self": 7.136121847968752, "children": { "_process_rank_one_or_two_observation": { "total": 30.602010455075288, "count": 181990, "is_parallel": true, "self": 30.602010455075288 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.0001847789999374072, "count": 1, "self": 0.0001847789999374072, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 469.6277103298962, "count": 703423, "is_parallel": true, "self": 16.097955859010654, "children": { "process_trajectory": { "total": 260.132135779887, "count": 703423, "is_parallel": true, "self": 259.58591072788704, "children": { "RLTrainer._checkpoint": { "total": 0.5462250519999543, "count": 4, "is_parallel": true, "self": 0.5462250519999543 } } }, "_update_policy": { "total": 193.39761869099857, "count": 90, "is_parallel": true, "self": 53.95243040497189, "children": { "TorchPPOOptimizer.update": { "total": 139.44518828602668, "count": 4587, "is_parallel": true, "self": 139.44518828602668 } } } } } } } } }, "TrainerController._save_models": { "total": 0.09823636900000565, "count": 1, "self": 0.0009884979999696952, "children": { "RLTrainer._checkpoint": { "total": 0.09724787100003596, "count": 1, "self": 0.09724787100003596 } } } } } } }