{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.7145135402679443, "min": 0.7145135402679443, "max": 2.8571181297302246, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 6790.73681640625, "min": 6790.73681640625, "max": 29165.4609375, "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": 12.894902229309082, "min": 0.4303753674030304, "max": 12.894902229309082, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2514.505859375, "min": 83.4928207397461, "max": 2608.371826171875, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06810770782060133, "min": 0.061461342185651247, "max": 0.07365632690055589, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2724308312824053, "min": 0.24584536874260499, "max": 0.3662926407654167, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.1798107788770222, "min": 0.11808123788225702, "max": 0.2834785580635071, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7192431155080888, "min": 0.4723249515290281, "max": 1.4173927903175354, "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": 25.772727272727273, "min": 3.6136363636363638, "max": 25.772727272727273, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1134.0, "min": 159.0, "max": 1395.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.772727272727273, "min": 3.6136363636363638, "max": 25.772727272727273, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1134.0, "min": 159.0, "max": 1395.0, "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": "1755667534", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yml --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": "1755667967" }, "total": 433.17356874300003, "count": 1, "self": 0.4383687380000083, "children": { "run_training.setup": { "total": 0.02317725500006418, "count": 1, "self": 0.02317725500006418 }, "TrainerController.start_learning": { "total": 432.71202274999996, "count": 1, "self": 0.39376770599437805, "children": { "TrainerController._reset_env": { "total": 2.7921324709998316, "count": 1, "self": 2.7921324709998316 }, "TrainerController.advance": { "total": 429.4333780990057, "count": 18192, "self": 0.39061162100801994, "children": { "env_step": { "total": 307.5378625570129, "count": 18192, "self": 236.91784132001317, "children": { "SubprocessEnvManager._take_step": { "total": 70.3906266770025, "count": 18192, "self": 1.2997659410054894, "children": { "TorchPolicy.evaluate": { "total": 69.09086073599701, "count": 18192, "self": 69.09086073599701 } } }, "workers": { "total": 0.22939455999721758, "count": 18192, "self": 0.0, "children": { "worker_root": { "total": 431.3475525870206, "count": 18192, "is_parallel": true, "self": 223.64364982202233, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.004450485000006665, "count": 1, "is_parallel": true, "self": 0.003095531999861123, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013549530001455423, "count": 10, "is_parallel": true, "self": 0.0013549530001455423 } } }, "UnityEnvironment.step": { "total": 0.03779092700006004, "count": 1, "is_parallel": true, "self": 0.0006053960000826919, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004167950000919518, "count": 1, "is_parallel": true, "self": 0.0004167950000919518 }, "communicator.exchange": { "total": 0.03477425199980644, "count": 1, "is_parallel": true, "self": 0.03477425199980644 }, "steps_from_proto": { "total": 0.0019944840000789554, "count": 1, "is_parallel": true, "self": 0.0003792780003095686, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016152059997693868, "count": 10, "is_parallel": true, "self": 0.0016152059997693868 } } } } } } }, "UnityEnvironment.step": { "total": 207.70390276499825, "count": 18191, "is_parallel": true, "self": 9.79503565697678, "children": { "UnityEnvironment._generate_step_input": { "total": 5.499716150010499, "count": 18191, "is_parallel": true, "self": 5.499716150010499 }, "communicator.exchange": { "total": 159.8182135730101, "count": 18191, "is_parallel": true, "self": 159.8182135730101 }, "steps_from_proto": { "total": 32.59093738500087, "count": 18191, "is_parallel": true, "self": 5.866380235982433, "children": { "_process_rank_one_or_two_observation": { "total": 26.724557149018437, "count": 181910, "is_parallel": true, "self": 26.724557149018437 } } } } } } } } } } }, "trainer_advance": { "total": 121.50490392098482, "count": 18192, "self": 0.4873538429906148, "children": { "process_trajectory": { "total": 26.66258409499528, "count": 18192, "self": 26.190035167995347, "children": { "RLTrainer._checkpoint": { "total": 0.47254892699993434, "count": 4, "self": 0.47254892699993434 } } }, "_update_policy": { "total": 94.35496598299892, "count": 90, "self": 39.22420686298233, "children": { "TorchPPOOptimizer.update": { "total": 55.13075912001659, "count": 4587, "self": 55.13075912001659 } } } } } } }, "trainer_threads": { "total": 9.550001323077595e-07, "count": 1, "self": 9.550001323077595e-07 }, "TrainerController._save_models": { "total": 0.09274351899989597, "count": 1, "self": 0.0012608509998699446, "children": { "RLTrainer._checkpoint": { "total": 0.09148266800002602, "count": 1, "self": 0.09148266800002602 } } } } } } }