{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.8280081748962402, "min": 0.8280081748962402, "max": 2.8203797340393066, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 7869.3896484375, "min": 7869.3896484375, "max": 28790.4375, "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": 13.064228057861328, "min": 0.49203726649284363, "max": 13.064228057861328, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2547.5244140625, "min": 95.45523071289062, "max": 2647.556396484375, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06829172943481336, "min": 0.06490567658357915, "max": 0.0732994024037194, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.27316691773925345, "min": 0.2596227063343166, "max": 0.36311297865547965, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.20204349256613674, "min": 0.1252179625512594, "max": 0.2819245781968622, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.808173970264547, "min": 0.5008718502050375, "max": 1.3839896359280046, "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": 25.977272727272727, "min": 3.6363636363636362, "max": 25.977272727272727, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1143.0, "min": 160.0, "max": 1405.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.977272727272727, "min": 3.6363636363636362, "max": 25.977272727272727, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1143.0, "min": 160.0, "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": "1738418104", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "command_line_arguments": "/home/sugarblock/miniconda3/envs/mlagents/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --force --no-graphics", "mlagents_version": "1.1.0", "mlagents_envs_version": "1.1.0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.2.2+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1738418386" }, "total": 306.9312917919999, "count": 1, "self": 0.2236873399997421, "children": { "run_training.setup": { "total": 0.01096974200004297, "count": 1, "self": 0.01096974200004297 }, "TrainerController.start_learning": { "total": 306.6966347100001, "count": 1, "self": 0.24586321100525765, "children": { "TrainerController._reset_env": { "total": 1.6424167629999147, "count": 1, "self": 1.6424167629999147 }, "TrainerController.advance": { "total": 304.7500493169948, "count": 18192, "self": 0.22392473801551205, "children": { "env_step": { "total": 185.05631220498913, "count": 18192, "self": 109.1621945549756, "children": { "SubprocessEnvManager._take_step": { "total": 75.73357555300049, "count": 18192, "self": 0.6702230629992982, "children": { "TorchPolicy.evaluate": { "total": 75.0633524900012, "count": 18192, "self": 75.0633524900012 } } }, "workers": { "total": 0.16054209701303535, "count": 18192, "self": 0.0, "children": { "worker_root": { "total": 305.83400912499724, "count": 18192, "is_parallel": true, "self": 211.32613035699126, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0018917090000059034, "count": 1, "is_parallel": true, "self": 0.0009131199997227668, "children": { "_process_rank_one_or_two_observation": { "total": 0.0009785890002831366, "count": 10, "is_parallel": true, "self": 0.0009785890002831366 } } }, "UnityEnvironment.step": { "total": 0.01553572400007397, "count": 1, "is_parallel": true, "self": 0.00016711800014945766, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00016355799994016706, "count": 1, "is_parallel": true, "self": 0.00016355799994016706 }, "communicator.exchange": { "total": 0.014575368999999228, "count": 1, "is_parallel": true, "self": 0.014575368999999228 }, "steps_from_proto": { "total": 0.0006296789999851171, "count": 1, "is_parallel": true, "self": 0.00014484499990885524, "children": { "_process_rank_one_or_two_observation": { "total": 0.00048483400007626187, "count": 10, "is_parallel": true, "self": 0.00048483400007626187 } } } } } } }, "UnityEnvironment.step": { "total": 94.50787876800598, "count": 18191, "is_parallel": true, "self": 2.7842707360049417, "children": { "UnityEnvironment._generate_step_input": { "total": 1.6114823300046055, "count": 18191, "is_parallel": true, "self": 1.6114823300046055 }, "communicator.exchange": { "total": 80.96843653399651, "count": 18191, "is_parallel": true, "self": 80.96843653399651 }, "steps_from_proto": { "total": 9.143689167999923, "count": 18191, "is_parallel": true, "self": 2.0655457910044106, "children": { "_process_rank_one_or_two_observation": { "total": 7.078143376995513, "count": 181910, "is_parallel": true, "self": 7.078143376995513 } } } } } } } } } } }, "trainer_advance": { "total": 119.46981237399018, "count": 18192, "self": 0.32723269898497165, "children": { "process_trajectory": { "total": 21.64562300000523, "count": 18192, "self": 21.370778402005158, "children": { "RLTrainer._checkpoint": { "total": 0.27484459800007244, "count": 4, "self": 0.27484459800007244 } } }, "_update_policy": { "total": 97.49695667499998, "count": 90, "self": 21.915703145002453, "children": { "TorchPPOOptimizer.update": { "total": 75.58125352999753, "count": 4587, "self": 75.58125352999753 } } } } } } }, "trainer_threads": { "total": 5.860001692781225e-07, "count": 1, "self": 5.860001692781225e-07 }, "TrainerController._save_models": { "total": 0.05830483299996558, "count": 1, "self": 0.0007298230000287731, "children": { "RLTrainer._checkpoint": { "total": 0.05757500999993681, "count": 1, "self": 0.05757500999993681 } } } } } } }