{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.8141961693763733, "min": 0.8099528551101685, "max": 2.869523048400879, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 7791.857421875, "min": 7791.857421875, "max": 29449.9140625, "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": 12.845467567443848, "min": 0.4853851795196533, "max": 12.845467567443848, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2504.8662109375, "min": 94.16472625732422, "max": 2605.921875, "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": 0.07395528463501821, "min": 0.06321258043919406, "max": 0.07395528463501821, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.29582113854007286, "min": 0.2553269936832686, "max": 0.3603863215857145, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.21032436294298548, "min": 0.15791704305721557, "max": 0.3062097484282419, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8412974517719419, "min": 0.6316681722288623, "max": 1.4453065515148873, "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": 25.386363636363637, "min": 4.090909090909091, "max": 25.527272727272727, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1117.0, "min": 180.0, "max": 1404.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.386363636363637, "min": 4.090909090909091, "max": 25.527272727272727, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1117.0, "min": 180.0, "max": 1404.0, "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": "1714681581", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]", "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": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.2.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1714682171" }, "total": 590.3417136810003, "count": 1, "self": 0.5438003549988935, "children": { "run_training.setup": { "total": 0.08133920900036173, "count": 1, "self": 0.08133920900036173 }, "TrainerController.start_learning": { "total": 589.7165741170011, "count": 1, "self": 0.8176380189852352, "children": { "TrainerController._reset_env": { "total": 4.201070445998994, "count": 1, "self": 4.201070445998994 }, "TrainerController.advance": { "total": 584.594925547015, "count": 18202, "self": 0.4376823820039135, "children": { "env_step": { "total": 584.1572431650111, "count": 18202, "self": 449.28699748284635, "children": { "SubprocessEnvManager._take_step": { "total": 134.4550027039768, "count": 18202, "self": 2.3195755350170657, "children": { "TorchPolicy.evaluate": { "total": 132.13542716895972, "count": 18202, "self": 132.13542716895972 } } }, "workers": { "total": 0.41524297818796185, "count": 18202, "self": 0.0, "children": { "worker_root": { "total": 587.7515290108731, "count": 18202, "is_parallel": true, "self": 277.21118407170434, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.008401156001127674, "count": 1, "is_parallel": true, "self": 0.00548769600209198, "children": { "_process_rank_one_or_two_observation": { "total": 0.0029134599990356946, "count": 10, "is_parallel": true, "self": 0.0029134599990356946 } } }, "UnityEnvironment.step": { "total": 0.046563953001168557, "count": 1, "is_parallel": true, "self": 0.0008321620007336605, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00047068700041563716, "count": 1, "is_parallel": true, "self": 0.00047068700041563716 }, "communicator.exchange": { "total": 0.04285785600040981, "count": 1, "is_parallel": true, "self": 0.04285785600040981 }, "steps_from_proto": { "total": 0.002403247999609448, "count": 1, "is_parallel": true, "self": 0.0004528250010480406, "children": { "_process_rank_one_or_two_observation": { "total": 0.0019504229985614074, "count": 10, "is_parallel": true, "self": 0.0019504229985614074 } } } } } } }, "UnityEnvironment.step": { "total": 310.5403449391688, "count": 18201, "is_parallel": true, "self": 14.987825485606663, "children": { "UnityEnvironment._generate_step_input": { "total": 7.530505484108289, "count": 18201, "is_parallel": true, "self": 7.530505484108289 }, "communicator.exchange": { "total": 243.64209565323472, "count": 18201, "is_parallel": true, "self": 243.64209565323472 }, "steps_from_proto": { "total": 44.37991831621912, "count": 18201, "is_parallel": true, "self": 8.835639714114222, "children": { "_process_rank_one_or_two_observation": { "total": 35.544278602104896, "count": 182010, "is_parallel": true, "self": 35.544278602104896 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.0004197350008325884, "count": 1, "self": 0.0004197350008325884, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 577.8157861361342, "count": 760136, "is_parallel": true, "self": 17.47288765751182, "children": { "process_trajectory": { "total": 305.05922982460834, "count": 760136, "is_parallel": true, "self": 304.1687803166078, "children": { "RLTrainer._checkpoint": { "total": 0.890449508000529, "count": 4, "is_parallel": true, "self": 0.890449508000529 } } }, "_update_policy": { "total": 255.28366865401404, "count": 90, "is_parallel": true, "self": 73.32214366898188, "children": { "TorchPPOOptimizer.update": { "total": 181.96152498503216, "count": 4587, "is_parallel": true, "self": 181.96152498503216 } } } } } } } } }, "TrainerController._save_models": { "total": 0.10252037000100245, "count": 1, "self": 0.0013813750010740478, "children": { "RLTrainer._checkpoint": { "total": 0.1011389949999284, "count": 1, "self": 0.1011389949999284 } } } } } } }