{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.1267740726470947, "min": 1.1267740726470947, "max": 2.874922513961792, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 10795.6220703125, "min": 10795.6220703125, "max": 29536.953125, "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": 12.457562446594238, "min": 0.4340077042579651, "max": 12.457562446594238, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2429.224609375, "min": 84.19749450683594, "max": 2493.00048828125, "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": 0.06689958804724716, "min": 0.06290343934418999, "max": 0.07709801059536403, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.26759835218898864, "min": 0.26074268133418754, "max": 0.36521570256673824, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.2038862613194129, "min": 0.11257207941711314, "max": 0.27098822586384474, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8155450452776516, "min": 0.45028831766845256, "max": 1.3441393766917435, "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": 24.5, "min": 2.909090909090909, "max": 24.5, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1078.0, "min": 128.0, "max": 1346.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 24.5, "min": 2.909090909090909, "max": 24.5, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1078.0, "min": 128.0, "max": 1346.0, "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": "1734830244", "python_version": "3.10.12 (main, Nov 6 2024, 20:22:13) [GCC 11.4.0]", "command_line_arguments": "/home/vscode/.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": "2.5.1+cu124", "numpy_version": "1.23.5", "end_time_seconds": "1734830576" }, "total": 331.9028437140005, "count": 1, "self": 0.474280534999707, "children": { "run_training.setup": { "total": 0.04218745899925125, "count": 1, "self": 0.04218745899925125 }, "TrainerController.start_learning": { "total": 331.3863757200015, "count": 1, "self": 0.4308585048929672, "children": { "TrainerController._reset_env": { "total": 4.027840693001053, "count": 1, "self": 4.027840693001053 }, "TrainerController.advance": { "total": 326.8188069571079, "count": 18209, "self": 0.20260516988128074, "children": { "env_step": { "total": 326.6162017872266, "count": 18209, "self": 259.59416884987513, "children": { "SubprocessEnvManager._take_step": { "total": 66.81118004836753, "count": 18209, "self": 1.1402526641686563, "children": { "TorchPolicy.evaluate": { "total": 65.67092738419888, "count": 18209, "self": 65.67092738419888 } } }, "workers": { "total": 0.21085288898393628, "count": 18209, "self": 0.0, "children": { "worker_root": { "total": 330.6570750361316, "count": 18209, "is_parallel": true, "self": 142.57170759897417, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0019350370021129493, "count": 1, "is_parallel": true, "self": 0.0005614760048047174, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013735609973082319, "count": 10, "is_parallel": true, "self": 0.0013735609973082319 } } }, "UnityEnvironment.step": { "total": 0.02228339499924914, "count": 1, "is_parallel": true, "self": 0.0003154009973513894, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0002375170006416738, "count": 1, "is_parallel": true, "self": 0.0002375170006416738 }, "communicator.exchange": { "total": 0.020916853998642182, "count": 1, "is_parallel": true, "self": 0.020916853998642182 }, "steps_from_proto": { "total": 0.0008136230026138946, "count": 1, "is_parallel": true, "self": 0.00019884400171577, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006147790008981247, "count": 10, "is_parallel": true, "self": 0.0006147790008981247 } } } } } } }, "UnityEnvironment.step": { "total": 188.0853674371574, "count": 18208, "is_parallel": true, "self": 4.596227572001226, "children": { "UnityEnvironment._generate_step_input": { "total": 2.7097099801576405, "count": 18208, "is_parallel": true, "self": 2.7097099801576405 }, "communicator.exchange": { "total": 166.82013903385086, "count": 18208, "is_parallel": true, "self": 166.82013903385086 }, "steps_from_proto": { "total": 13.95929085114767, "count": 18208, "is_parallel": true, "self": 3.3975848144800693, "children": { "_process_rank_one_or_two_observation": { "total": 10.561706036667601, "count": 182080, "is_parallel": true, "self": 10.561706036667601 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00019187599900760688, "count": 1, "self": 0.00019187599900760688, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 324.9403932249661, "count": 281415, "is_parallel": true, "self": 5.720903608631488, "children": { "process_trajectory": { "total": 179.9420745453208, "count": 281415, "is_parallel": true, "self": 179.3076142473219, "children": { "RLTrainer._checkpoint": { "total": 0.6344602979988849, "count": 4, "is_parallel": true, "self": 0.6344602979988849 } } }, "_update_policy": { "total": 139.27741507101382, "count": 90, "is_parallel": true, "self": 34.63973974009059, "children": { "TorchPPOOptimizer.update": { "total": 104.63767533092323, "count": 4587, "is_parallel": true, "self": 104.63767533092323 } } } } } } } } }, "TrainerController._save_models": { "total": 0.10867768900061492, "count": 1, "self": 0.022836290998384356, "children": { "RLTrainer._checkpoint": { "total": 0.08584139800223056, "count": 1, "self": 0.08584139800223056 } } } } } } }