{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.8456804752349854, "min": 0.8439781665802002, "max": 2.8646697998046875, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8093.162109375, "min": 8093.162109375, "max": 29463.12890625, "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": 12.847467422485352, "min": 0.36009976267814636, "max": 12.847467422485352, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2505.256103515625, "min": 69.8593521118164, "max": 2596.0810546875, "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": 0.06599480069088909, "min": 0.06385080164992342, "max": 0.07360954000026801, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.26397920276355635, "min": 0.26031996812968167, "max": 0.36804770000134, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.20789479004109607, "min": 0.12717219526359044, "max": 0.31687510495676713, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8315791601643843, "min": 0.5086887810543618, "max": 1.4395639186396318, "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": 25.136363636363637, "min": 3.5, "max": 25.25, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1106.0, "min": 154.0, "max": 1380.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.136363636363637, "min": 3.5, "max": 25.25, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1106.0, "min": 154.0, "max": 1380.0, "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": "1681004078", "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": "1681004543" }, "total": 464.91879637299996, "count": 1, "self": 0.4393087319999722, "children": { "run_training.setup": { "total": 0.11653908399998159, "count": 1, "self": 0.11653908399998159 }, "TrainerController.start_learning": { "total": 464.362948557, "count": 1, "self": 0.543769283998472, "children": { "TrainerController._reset_env": { "total": 4.022169009999999, "count": 1, "self": 4.022169009999999 }, "TrainerController.advance": { "total": 459.6394134950015, "count": 18204, "self": 0.2963221620040031, "children": { "env_step": { "total": 459.3430913329975, "count": 18204, "self": 333.9842071559981, "children": { "SubprocessEnvManager._take_step": { "total": 125.0768138870053, "count": 18204, "self": 2.0080318900013765, "children": { "TorchPolicy.evaluate": { "total": 123.06878199700392, "count": 18204, "self": 123.06878199700392 } } }, "workers": { "total": 0.28207028999409545, "count": 18204, "self": 0.0, "children": { "worker_root": { "total": 462.9268369479984, "count": 18204, "is_parallel": true, "self": 213.03574175599738, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005972323000008828, "count": 1, "is_parallel": true, "self": 0.004427363000047535, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015449599999612929, "count": 10, "is_parallel": true, "self": 0.0015449599999612929 } } }, "UnityEnvironment.step": { "total": 0.03604170399998452, "count": 1, "is_parallel": true, "self": 0.0005851409999877433, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003796280000187835, "count": 1, "is_parallel": true, "self": 0.0003796280000187835 }, "communicator.exchange": { "total": 0.03320924299998751, "count": 1, "is_parallel": true, "self": 0.03320924299998751 }, "steps_from_proto": { "total": 0.001867691999990484, "count": 1, "is_parallel": true, "self": 0.00036453499996014216, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015031570000303418, "count": 10, "is_parallel": true, "self": 0.0015031570000303418 } } } } } } }, "UnityEnvironment.step": { "total": 249.89109519200105, "count": 18203, "is_parallel": true, "self": 10.217961112000921, "children": { "UnityEnvironment._generate_step_input": { "total": 5.438350289994304, "count": 18203, "is_parallel": true, "self": 5.438350289994304 }, "communicator.exchange": { "total": 201.64875180800144, "count": 18203, "is_parallel": true, "self": 201.64875180800144 }, "steps_from_proto": { "total": 32.586031982004386, "count": 18203, "is_parallel": true, "self": 6.435113118049571, "children": { "_process_rank_one_or_two_observation": { "total": 26.150918863954814, "count": 182030, "is_parallel": true, "self": 26.150918863954814 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.0001690959999223196, "count": 1, "self": 0.0001690959999223196, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 456.07524792402876, "count": 424129, "is_parallel": true, "self": 10.425277316019844, "children": { "process_trajectory": { "total": 249.93611854000875, "count": 424129, "is_parallel": true, "self": 248.92249078400874, "children": { "RLTrainer._checkpoint": { "total": 1.0136277560000053, "count": 4, "is_parallel": true, "self": 1.0136277560000053 } } }, "_update_policy": { "total": 195.71385206800016, "count": 90, "is_parallel": true, "self": 73.33929653999931, "children": { "TorchPPOOptimizer.update": { "total": 122.37455552800085, "count": 4584, "is_parallel": true, "self": 122.37455552800085 } } } } } } } } }, "TrainerController._save_models": { "total": 0.15742767200003982, "count": 1, "self": 0.0011171720001357244, "children": { "RLTrainer._checkpoint": { "total": 0.1563104999999041, "count": 1, "self": 0.1563104999999041 } } } } } } }