{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9433662295341492, "min": 0.9433662295341492, "max": 2.8598148822784424, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9038.3916015625, "min": 9038.3916015625, "max": 29287.36328125, "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": 13.082194328308105, "min": 0.2533191442489624, "max": 13.082194328308105, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2551.02783203125, "min": 49.14391326904297, "max": 2664.886474609375, "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": 0.06737742921669611, "min": 0.06193267383256599, "max": 0.07250561462826548, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.26950971686678443, "min": 0.24932746694870658, "max": 0.35376011237302935, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.205722152456349, "min": 0.14965139588514598, "max": 0.2727865378646289, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.822888609825396, "min": 0.5986055835405839, "max": 1.3639326893231447, "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": 25.75, "min": 4.090909090909091, "max": 26.136363636363637, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1133.0, "min": 180.0, "max": 1395.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.75, "min": 4.090909090909091, "max": 26.136363636363637, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1133.0, "min": 180.0, "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": "1719729567", "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": "2.3.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1719730081" }, "total": 514.0082939370001, "count": 1, "self": 0.8046894340000108, "children": { "run_training.setup": { "total": 0.06177342000000863, "count": 1, "self": 0.06177342000000863 }, "TrainerController.start_learning": { "total": 513.141831083, "count": 1, "self": 0.7206411780024382, "children": { "TrainerController._reset_env": { "total": 3.0128971329999104, "count": 1, "self": 3.0128971329999104 }, "TrainerController.advance": { "total": 509.2599672259977, "count": 18212, "self": 0.3328535250010418, "children": { "env_step": { "total": 508.92711370099664, "count": 18212, "self": 334.03143326699126, "children": { "SubprocessEnvManager._take_step": { "total": 174.54661883199685, "count": 18212, "self": 1.7657461270066506, "children": { "TorchPolicy.evaluate": { "total": 172.7808727049902, "count": 18212, "self": 172.7808727049902 } } }, "workers": { "total": 0.34906160200853265, "count": 18212, "self": 0.0, "children": { "worker_root": { "total": 511.6480246489946, "count": 18212, "is_parallel": true, "self": 256.05236356599937, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005728718000000299, "count": 1, "is_parallel": true, "self": 0.0039042289999997593, "children": { "_process_rank_one_or_two_observation": { "total": 0.0018244890000005398, "count": 10, "is_parallel": true, "self": 0.0018244890000005398 } } }, "UnityEnvironment.step": { "total": 0.08209047699995153, "count": 1, "is_parallel": true, "self": 0.0007218869998268929, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00041811600010532857, "count": 1, "is_parallel": true, "self": 0.00041811600010532857 }, "communicator.exchange": { "total": 0.07403661499995451, "count": 1, "is_parallel": true, "self": 0.07403661499995451 }, "steps_from_proto": { "total": 0.006913859000064804, "count": 1, "is_parallel": true, "self": 0.005062936000058471, "children": { "_process_rank_one_or_two_observation": { "total": 0.0018509230000063326, "count": 10, "is_parallel": true, "self": 0.0018509230000063326 } } } } } } }, "UnityEnvironment.step": { "total": 255.5956610829952, "count": 18211, "is_parallel": true, "self": 11.61781176798877, "children": { "UnityEnvironment._generate_step_input": { "total": 6.113855548987431, "count": 18211, "is_parallel": true, "self": 6.113855548987431 }, "communicator.exchange": { "total": 199.5698387470104, "count": 18211, "is_parallel": true, "self": 199.5698387470104 }, "steps_from_proto": { "total": 38.2941550190086, "count": 18211, "is_parallel": true, "self": 7.545800011988717, "children": { "_process_rank_one_or_two_observation": { "total": 30.74835500701988, "count": 182110, "is_parallel": true, "self": 30.74835500701988 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00021018300003561308, "count": 1, "self": 0.00021018300003561308, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 502.94672857392914, "count": 752804, "is_parallel": true, "self": 16.094636713891532, "children": { "process_trajectory": { "total": 281.36657633903644, "count": 752804, "is_parallel": true, "self": 280.1528152270363, "children": { "RLTrainer._checkpoint": { "total": 1.2137611120001566, "count": 4, "is_parallel": true, "self": 1.2137611120001566 } } }, "_update_policy": { "total": 205.48551552100116, "count": 90, "is_parallel": true, "self": 62.56441803700477, "children": { "TorchPPOOptimizer.update": { "total": 142.9210974839964, "count": 4587, "is_parallel": true, "self": 142.9210974839964 } } } } } } } } }, "TrainerController._save_models": { "total": 0.14811536299998806, "count": 1, "self": 0.0014417770000818564, "children": { "RLTrainer._checkpoint": { "total": 0.1466735859999062, "count": 1, "self": 0.1466735859999062 } } } } } } }