{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.8919032216072083, "min": 0.8919032216072083, "max": 2.872331380844116, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8525.703125, "min": 8525.703125, "max": 29415.546875, "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": 12.914673805236816, "min": 0.33305370807647705, "max": 12.914673805236816, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2518.361328125, "min": 64.61241912841797, "max": 2608.82763671875, "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": 0.07152451092021211, "min": 0.0632748559934884, "max": 0.0737611127662211, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.28609804368084846, "min": 0.2530994239739536, "max": 0.36121205297440256, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.1970834562591478, "min": 0.11382793169354508, "max": 0.30025076533065126, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7883338250365912, "min": 0.4553117267741803, "max": 1.5012538266532562, "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": 3.3636363636363638, "max": 25.477272727272727, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1117.0, "min": 148.0, "max": 1376.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.386363636363637, "min": 3.3636363636363638, "max": 25.477272727272727, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1117.0, "min": 148.0, "max": 1376.0, "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": "1691851095", "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [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": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.11.0+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1691851595" }, "total": 499.45697965499994, "count": 1, "self": 0.43344772800003284, "children": { "run_training.setup": { "total": 0.04479314799993972, "count": 1, "self": 0.04479314799993972 }, "TrainerController.start_learning": { "total": 498.97873877899997, "count": 1, "self": 0.5736089910049031, "children": { "TrainerController._reset_env": { "total": 4.130036519999976, "count": 1, "self": 4.130036519999976 }, "TrainerController.advance": { "total": 494.1281509109949, "count": 18201, "self": 0.3010479290155672, "children": { "env_step": { "total": 493.82710298197935, "count": 18201, "self": 360.8315152299846, "children": { "SubprocessEnvManager._take_step": { "total": 132.69056835999368, "count": 18201, "self": 1.8557931500096174, "children": { "TorchPolicy.evaluate": { "total": 130.83477520998406, "count": 18201, "self": 130.83477520998406 } } }, "workers": { "total": 0.30501939200109973, "count": 18201, "self": 0.0, "children": { "worker_root": { "total": 497.1488135510125, "count": 18201, "is_parallel": true, "self": 232.50329652901382, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.00660474799997246, "count": 1, "is_parallel": true, "self": 0.004986788999985947, "children": { "_process_rank_one_or_two_observation": { "total": 0.001617958999986513, "count": 10, "is_parallel": true, "self": 0.001617958999986513 } } }, "UnityEnvironment.step": { "total": 0.04762846100004481, "count": 1, "is_parallel": true, "self": 0.0006828740001765254, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003280439999571172, "count": 1, "is_parallel": true, "self": 0.0003280439999571172 }, "communicator.exchange": { "total": 0.04448022199994739, "count": 1, "is_parallel": true, "self": 0.04448022199994739 }, "steps_from_proto": { "total": 0.0021373209999637766, "count": 1, "is_parallel": true, "self": 0.00037354499988850876, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017637760000752678, "count": 10, "is_parallel": true, "self": 0.0017637760000752678 } } } } } } }, "UnityEnvironment.step": { "total": 264.64551702199867, "count": 18200, "is_parallel": true, "self": 11.033877337999797, "children": { "UnityEnvironment._generate_step_input": { "total": 5.676095523998697, "count": 18200, "is_parallel": true, "self": 5.676095523998697 }, "communicator.exchange": { "total": 208.52117158900228, "count": 18200, "is_parallel": true, "self": 208.52117158900228 }, "steps_from_proto": { "total": 39.4143725709979, "count": 18200, "is_parallel": true, "self": 7.297273763980456, "children": { "_process_rank_one_or_two_observation": { "total": 32.11709880701744, "count": 182000, "is_parallel": true, "self": 32.11709880701744 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00015133300007619255, "count": 1, "self": 0.00015133300007619255, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 490.0671849149844, "count": 463704, "is_parallel": true, "self": 10.994759638976802, "children": { "process_trajectory": { "total": 270.3266739380082, "count": 463704, "is_parallel": true, "self": 269.51350201900823, "children": { "RLTrainer._checkpoint": { "total": 0.8131719189999558, "count": 4, "is_parallel": true, "self": 0.8131719189999558 } } }, "_update_policy": { "total": 208.74575133799942, "count": 90, "is_parallel": true, "self": 81.80931167700226, "children": { "TorchPPOOptimizer.update": { "total": 126.93643966099717, "count": 4587, "is_parallel": true, "self": 126.93643966099717 } } } } } } } } }, "TrainerController._save_models": { "total": 0.1467910240000947, "count": 1, "self": 0.000872205000177928, "children": { "RLTrainer._checkpoint": { "total": 0.14591881899991677, "count": 1, "self": 0.14591881899991677 } } } } } } }