{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.7868654131889343, "min": 0.7868654131889343, "max": 2.8324368000030518, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 7478.369140625, "min": 7478.369140625, "max": 28913.515625, "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": 12.760157585144043, "min": 0.4782947301864624, "max": 12.760157585144043, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2488.230712890625, "min": 92.78917694091797, "max": 2567.758056640625, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06340046717748776, "min": 0.05596588276627397, "max": 0.0738292254820265, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.25360186870995105, "min": 0.24813916412063453, "max": 0.36914612741013253, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.2076249013782716, "min": 0.14200761302502132, "max": 0.29115843407663644, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8304996055130864, "min": 0.5680304521000853, "max": 1.3971605321355893, "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.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.Environment.CumulativeReward.mean": { "value": 24.84090909090909, "min": 3.840909090909091, "max": 25.545454545454547, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1093.0, "min": 169.0, "max": 1405.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 24.84090909090909, "min": 3.840909090909091, "max": 25.545454545454547, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1093.0, "min": 169.0, "max": 1405.0, "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": "1781875671", "python_version": "3.10.11 (main, May 16 2023, 00:28:57) [GCC 11.2.0]", "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": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.8.0+cu128", "numpy_version": "1.23.5", "end_time_seconds": "1781876127" }, "total": 456.52546919400004, "count": 1, "self": 0.7454472940000869, "children": { "run_training.setup": { "total": 0.025794471000040176, "count": 1, "self": 0.025794471000040176 }, "TrainerController.start_learning": { "total": 455.7542274289999, "count": 1, "self": 0.37245737100454335, "children": { "TrainerController._reset_env": { "total": 3.3568154050000203, "count": 1, "self": 3.3568154050000203 }, "TrainerController.advance": { "total": 451.90620019199537, "count": 18192, "self": 0.36457322998376185, "children": { "env_step": { "total": 332.92785049499264, "count": 18192, "self": 259.90105158795393, "children": { "SubprocessEnvManager._take_step": { "total": 72.80633241102555, "count": 18192, "self": 1.2805479390153778, "children": { "TorchPolicy.evaluate": { "total": 71.52578447201017, "count": 18192, "self": 71.52578447201017 } } }, "workers": { "total": 0.22046649601315949, "count": 18192, "self": 0.0, "children": { "worker_root": { "total": 453.6822238050048, "count": 18192, "is_parallel": true, "self": 224.94271435099813, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.004637362000039502, "count": 1, "is_parallel": true, "self": 0.003012975000501683, "children": { "_process_rank_one_or_two_observation": { "total": 0.001624386999537819, "count": 10, "is_parallel": true, "self": 0.001624386999537819 } } }, "UnityEnvironment.step": { "total": 0.039207859000043754, "count": 1, "is_parallel": true, "self": 0.0006201699999337507, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004170490000205973, "count": 1, "is_parallel": true, "self": 0.0004170490000205973 }, "communicator.exchange": { "total": 0.03627350700003262, "count": 1, "is_parallel": true, "self": 0.03627350700003262 }, "steps_from_proto": { "total": 0.0018971330000567832, "count": 1, "is_parallel": true, "self": 0.00036522800007787737, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015319049999789058, "count": 10, "is_parallel": true, "self": 0.0015319049999789058 } } } } } } }, "UnityEnvironment.step": { "total": 228.73950945400668, "count": 18191, "is_parallel": true, "self": 10.457848932026195, "children": { "UnityEnvironment._generate_step_input": { "total": 5.5591193259815554, "count": 18191, "is_parallel": true, "self": 5.5591193259815554 }, "communicator.exchange": { "total": 175.10133291400734, "count": 18191, "is_parallel": true, "self": 175.10133291400734 }, "steps_from_proto": { "total": 37.621208281991585, "count": 18191, "is_parallel": true, "self": 6.698501413962958, "children": { "_process_rank_one_or_two_observation": { "total": 30.922706868028627, "count": 181910, "is_parallel": true, "self": 30.922706868028627 } } } } } } } } } } }, "trainer_advance": { "total": 118.61377646701897, "count": 18192, "self": 0.4417191080108296, "children": { "process_trajectory": { "total": 24.646179804007716, "count": 18192, "self": 24.20995907500776, "children": { "RLTrainer._checkpoint": { "total": 0.436220728999956, "count": 4, "self": 0.436220728999956 } } }, "_update_policy": { "total": 93.52587755500042, "count": 90, "self": 37.550121010001476, "children": { "TorchPPOOptimizer.update": { "total": 55.975756544998944, "count": 4587, "self": 55.975756544998944 } } } } } } }, "trainer_threads": { "total": 1.2989999049750622e-06, "count": 1, "self": 1.2989999049750622e-06 }, "TrainerController._save_models": { "total": 0.11875316200007546, "count": 1, "self": 0.0008831670002109604, "children": { "RLTrainer._checkpoint": { "total": 0.1178699949998645, "count": 1, "self": 0.1178699949998645 } } } } } } }