{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9485373497009277, "min": 0.9485373497009277, "max": 2.873049259185791, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9067.068359375, "min": 9067.068359375, "max": 29454.501953125, "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": 12.93319320678711, "min": 0.3325102925300598, "max": 12.93319320678711, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2521.97265625, "min": 64.50699615478516, "max": 2594.65771484375, "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": 0.06782068043271554, "min": 0.06208070084377302, "max": 0.07323863881631007, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.27128272173086215, "min": 0.2537003646686892, "max": 0.3589283416311838, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.183431216460817, "min": 0.12461841971654554, "max": 0.28237079251922814, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.733724865843268, "min": 0.49847367886618216, "max": 1.3372607325550683, "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": 25.977272727272727, "min": 3.25, "max": 25.977272727272727, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1143.0, "min": 143.0, "max": 1385.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.977272727272727, "min": 3.25, "max": 25.977272727272727, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1143.0, "min": 143.0, "max": 1385.0, "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": "1680166036", "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": "1680166501" }, "total": 465.2608386249999, "count": 1, "self": 0.434790917999635, "children": { "run_training.setup": { "total": 0.11285959399992862, "count": 1, "self": 0.11285959399992862 }, "TrainerController.start_learning": { "total": 464.71318811300034, "count": 1, "self": 0.5334779359614004, "children": { "TrainerController._reset_env": { "total": 9.56079726500002, "count": 1, "self": 9.56079726500002 }, "TrainerController.advance": { "total": 454.4833815910388, "count": 18201, "self": 0.28325914207471214, "children": { "env_step": { "total": 454.20012244896407, "count": 18201, "self": 326.6395422929627, "children": { "SubprocessEnvManager._take_step": { "total": 127.29145758003415, "count": 18201, "self": 2.255952151027941, "children": { "TorchPolicy.evaluate": { "total": 125.03550542900621, "count": 18201, "self": 125.03550542900621 } } }, "workers": { "total": 0.26912257596723066, "count": 18201, "self": 0.0, "children": { "worker_root": { "total": 463.17784865698786, "count": 18201, "is_parallel": true, "self": 223.90650719795076, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005535538000003726, "count": 1, "is_parallel": true, "self": 0.003844099000616552, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016914389993871737, "count": 10, "is_parallel": true, "self": 0.0016914389993871737 } } }, "UnityEnvironment.step": { "total": 0.0383643220002341, "count": 1, "is_parallel": true, "self": 0.0006655649999629532, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00027840800021294854, "count": 1, "is_parallel": true, "self": 0.00027840800021294854 }, "communicator.exchange": { "total": 0.035274545999982365, "count": 1, "is_parallel": true, "self": 0.035274545999982365 }, "steps_from_proto": { "total": 0.00214580300007583, "count": 1, "is_parallel": true, "self": 0.00043057799939560937, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017152250006802205, "count": 10, "is_parallel": true, "self": 0.0017152250006802205 } } } } } } }, "UnityEnvironment.step": { "total": 239.2713414590371, "count": 18200, "is_parallel": true, "self": 9.47870324204996, "children": { "UnityEnvironment._generate_step_input": { "total": 5.135317294957986, "count": 18200, "is_parallel": true, "self": 5.135317294957986 }, "communicator.exchange": { "total": 193.31814737100103, "count": 18200, "is_parallel": true, "self": 193.31814737100103 }, "steps_from_proto": { "total": 31.339173551028125, "count": 18200, "is_parallel": true, "self": 6.287351776063133, "children": { "_process_rank_one_or_two_observation": { "total": 25.051821774964992, "count": 182000, "is_parallel": true, "self": 25.051821774964992 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00011913200023627724, "count": 1, "self": 0.00011913200023627724, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 451.19165717178566, "count": 401476, "is_parallel": true, "self": 10.063154247747207, "children": { "process_trajectory": { "total": 249.17155950303822, "count": 401476, "is_parallel": true, "self": 248.09328618803784, "children": { "RLTrainer._checkpoint": { "total": 1.0782733150003878, "count": 4, "is_parallel": true, "self": 1.0782733150003878 } } }, "_update_policy": { "total": 191.95694342100023, "count": 90, "is_parallel": true, "self": 73.1135911870092, "children": { "TorchPPOOptimizer.update": { "total": 118.84335223399103, "count": 4584, "is_parallel": true, "self": 118.84335223399103 } } } } } } } } }, "TrainerController._save_models": { "total": 0.1354121889999078, "count": 1, "self": 0.0008863219995873806, "children": { "RLTrainer._checkpoint": { "total": 0.13452586700032043, "count": 1, "self": 0.13452586700032043 } } } } } } }