{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9204595685005188, "min": 0.8983811140060425, "max": 2.8713176250457764, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8788.5478515625, "min": 8696.3291015625, "max": 29405.1640625, "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": 12.93194580078125, "min": 0.29367753863334656, "max": 12.93194580078125, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2521.7294921875, "min": 56.97344207763672, "max": 2632.90869140625, "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": 0.0707010404888327, "min": 0.06113187128586087, "max": 0.07373128342784613, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2828041619553308, "min": 0.24452748514344347, "max": 0.3554524838235047, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.2045750609215568, "min": 0.1369055058640501, "max": 0.2773976273980795, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8183002436862272, "min": 0.5476220234562004, "max": 1.3869881369903976, "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": 3.477272727272727, "max": 25.681818181818183, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1110.0, "min": 153.0, "max": 1390.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.227272727272727, "min": 3.477272727272727, "max": 25.681818181818183, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1110.0, "min": 153.0, "max": 1390.0, "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": "1674285699", "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": "1.21.6", "end_time_seconds": "1674286108" }, "total": 409.170818532, "count": 1, "self": 0.38806603199998335, "children": { "run_training.setup": { "total": 0.10091621800000894, "count": 1, "self": 0.10091621800000894 }, "TrainerController.start_learning": { "total": 408.681836282, "count": 1, "self": 0.5128346589972921, "children": { "TrainerController._reset_env": { "total": 9.19582429899998, "count": 1, "self": 9.19582429899998 }, "TrainerController.advance": { "total": 398.85821385700257, "count": 18201, "self": 0.25341053999915175, "children": { "env_step": { "total": 398.6048033170034, "count": 18201, "self": 261.87958079799836, "children": { "SubprocessEnvManager._take_step": { "total": 136.47397762200472, "count": 18201, "self": 1.3436371630036774, "children": { "TorchPolicy.evaluate": { "total": 135.13034045900105, "count": 18201, "self": 29.85465833500848, "children": { "TorchPolicy.sample_actions": { "total": 105.27568212399257, "count": 18201, "self": 105.27568212399257 } } } } }, "workers": { "total": 0.25124489700033337, "count": 18201, "self": 0.0, "children": { "worker_root": { "total": 407.4626091129994, "count": 18201, "is_parallel": true, "self": 196.3145988759992, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.010329698000020926, "count": 1, "is_parallel": true, "self": 0.0038246649999678084, "children": { "_process_rank_one_or_two_observation": { "total": 0.006505033000053118, "count": 10, "is_parallel": true, "self": 0.006505033000053118 } } }, "UnityEnvironment.step": { "total": 0.029621223999981794, "count": 1, "is_parallel": true, "self": 0.0006445679999274034, "children": { "UnityEnvironment._generate_step_input": { "total": 0.000263043000018115, "count": 1, "is_parallel": true, "self": 0.000263043000018115 }, "communicator.exchange": { "total": 0.026863504999994348, "count": 1, "is_parallel": true, "self": 0.026863504999994348 }, "steps_from_proto": { "total": 0.0018501080000419279, "count": 1, "is_parallel": true, "self": 0.0004446579999353162, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014054500001066117, "count": 10, "is_parallel": true, "self": 0.0014054500001066117 } } } } } } }, "UnityEnvironment.step": { "total": 211.14801023700022, "count": 18200, "is_parallel": true, "self": 7.970149772016612, "children": { "UnityEnvironment._generate_step_input": { "total": 4.6836082559880765, "count": 18200, "is_parallel": true, "self": 4.6836082559880765 }, "communicator.exchange": { "total": 170.27513834999792, "count": 18200, "is_parallel": true, "self": 170.27513834999792 }, "steps_from_proto": { "total": 28.219113858997616, "count": 18200, "is_parallel": true, "self": 6.032663305985238, "children": { "_process_rank_one_or_two_observation": { "total": 22.186450553012378, "count": 182000, "is_parallel": true, "self": 22.186450553012378 } } } } } } } } } } } } }, "trainer_threads": { "total": 4.0649000084158615e-05, "count": 1, "self": 4.0649000084158615e-05, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 396.3346488650185, "count": 321656, "is_parallel": true, "self": 8.159042636043068, "children": { "process_trajectory": { "total": 227.2721514609758, "count": 321656, "is_parallel": true, "self": 226.25861150897583, "children": { "RLTrainer._checkpoint": { "total": 1.0135399519999737, "count": 4, "is_parallel": true, "self": 1.0135399519999737 } } }, "_update_policy": { "total": 160.90345476799962, "count": 90, "is_parallel": true, "self": 41.704433788998585, "children": { "TorchPPOOptimizer.update": { "total": 119.19902097900103, "count": 4584, "is_parallel": true, "self": 119.19902097900103 } } } } } } } } }, "TrainerController._save_models": { "total": 0.11492281800008186, "count": 1, "self": 0.0010845310000604513, "children": { "RLTrainer._checkpoint": { "total": 0.11383828700002141, "count": 1, "self": 0.11383828700002141 } } } } } } }