{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.948525071144104, "min": 0.948525071144104, "max": 2.8652477264404297, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9066.951171875, "min": 9066.951171875, "max": 29406.037109375, "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": 12.973207473754883, "min": 0.3863008916378021, "max": 12.973207473754883, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2529.775390625, "min": 74.94237518310547, "max": 2620.40771484375, "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": 0.07588126734538259, "min": 0.06383201489955478, "max": 0.07588126734538259, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.30352506938153034, "min": 0.25532805959821914, "max": 0.356467714498114, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.19605158868373612, "min": 0.10328806343479266, "max": 0.27717882862278065, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7842063547349445, "min": 0.41315225373917064, "max": 1.3858941431139031, "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": 25.65909090909091, "min": 2.977272727272727, "max": 25.65909090909091, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1129.0, "min": 131.0, "max": 1394.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.65909090909091, "min": 2.977272727272727, "max": 25.65909090909091, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1129.0, "min": 131.0, "max": 1394.0, "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": "1680284212", "python_version": "3.9.16 (main, Mar 8 2023, 14:00:05) \n[GCC 11.2.0]", "command_line_arguments": "/home/u/miniconda3/envs/huggingface-unity/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics --force", "mlagents_version": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.11.0", "numpy_version": "1.21.2", "end_time_seconds": "1680284533" }, "total": 320.75122395000017, "count": 1, "self": 0.21768646900000022, "children": { "run_training.setup": { "total": 0.0071148589995573275, "count": 1, "self": 0.0071148589995573275 }, "TrainerController.start_learning": { "total": 320.5264226220006, "count": 1, "self": 0.25077017797866574, "children": { "TrainerController._reset_env": { "total": 2.2422614650004107, "count": 1, "self": 2.2422614650004107 }, "TrainerController.advance": { "total": 317.94355877902217, "count": 18201, "self": 0.1255732189911214, "children": { "env_step": { "total": 317.81798556003105, "count": 18201, "self": 183.7982844709777, "children": { "SubprocessEnvManager._take_step": { "total": 133.89295002300332, "count": 18201, "self": 0.8289285209566515, "children": { "TorchPolicy.evaluate": { "total": 133.06402150204667, "count": 18201, "self": 133.06402150204667 } } }, "workers": { "total": 0.1267510660500193, "count": 18201, "self": 0.0, "children": { "worker_root": { "total": 319.8889944699995, "count": 18201, "is_parallel": true, "self": 185.58709164506035, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0009026980005728547, "count": 1, "is_parallel": true, "self": 0.0002647160008564242, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006379819997164304, "count": 10, "is_parallel": true, "self": 0.0006379819997164304 } } }, "UnityEnvironment.step": { "total": 0.01593817899993155, "count": 1, "is_parallel": true, "self": 0.00018892800017056288, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00015162799991230713, "count": 1, "is_parallel": true, "self": 0.00015162799991230713 }, "communicator.exchange": { "total": 0.015005291000306897, "count": 1, "is_parallel": true, "self": 0.015005291000306897 }, "steps_from_proto": { "total": 0.0005923319995417842, "count": 1, "is_parallel": true, "self": 0.00013659899923368357, "children": { "_process_rank_one_or_two_observation": { "total": 0.0004557330003081006, "count": 10, "is_parallel": true, "self": 0.0004557330003081006 } } } } } } }, "UnityEnvironment.step": { "total": 134.30190282493913, "count": 18200, "is_parallel": true, "self": 3.3185713517013937, "children": { "UnityEnvironment._generate_step_input": { "total": 1.8033410330672268, "count": 18200, "is_parallel": true, "self": 1.8033410330672268 }, "communicator.exchange": { "total": 119.24831985009587, "count": 18200, "is_parallel": true, "self": 119.24831985009587 }, "steps_from_proto": { "total": 9.931670590074646, "count": 18200, "is_parallel": true, "self": 2.0430779288954, "children": { "_process_rank_one_or_two_observation": { "total": 7.888592661179246, "count": 182000, "is_parallel": true, "self": 7.888592661179246 } } } } } } } } } } } } }, "trainer_threads": { "total": 4.312999953981489e-05, "count": 1, "self": 4.312999953981489e-05, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 316.38345145829953, "count": 335918, "is_parallel": true, "self": 4.256159947394735, "children": { "process_trajectory": { "total": 167.46870303490778, "count": 335918, "is_parallel": true, "self": 167.0169628799067, "children": { "RLTrainer._checkpoint": { "total": 0.4517401550010618, "count": 4, "is_parallel": true, "self": 0.4517401550010618 } } }, "_update_policy": { "total": 144.65858847599702, "count": 90, "is_parallel": true, "self": 23.708663277975575, "children": { "TorchPPOOptimizer.update": { "total": 120.94992519802145, "count": 4587, "is_parallel": true, "self": 120.94992519802145 } } } } } } } } }, "TrainerController._save_models": { "total": 0.08978906999982428, "count": 1, "self": 0.0005484129997057607, "children": { "RLTrainer._checkpoint": { "total": 0.08924065700011852, "count": 1, "self": 0.08924065700011852 } } } } } } }