{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.0642482042312622, "min": 1.0642482042312622, "max": 2.8687212467193604, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 10255.095703125, "min": 10255.095703125, "max": 29410.130859375, "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": 12.276300430297852, "min": 0.25306883454322815, "max": 12.276300430297852, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2393.878662109375, "min": 49.09535217285156, "max": 2463.5263671875, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 10945.0, "min": 8756.0, "max": 10945.0, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06569550941497379, "min": 0.06127656077482171, "max": 0.07171320597225728, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.26278203765989516, "min": 0.24675169745323194, "max": 0.3585660298612864, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.19996028057500426, "min": 0.10957741645032396, "max": 0.2720208467513907, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.799841122300017, "min": 0.4383096658012958, "max": 1.3313407661283718, "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": 24.181818181818183, "min": 3.2045454545454546, "max": 24.363636363636363, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1064.0, "min": 141.0, "max": 1340.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 24.181818181818183, "min": 3.2045454545454546, "max": 24.363636363636363, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1064.0, "min": 141.0, "max": 1340.0, "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": "1699296476", "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": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.1.0+cu118", "numpy_version": "1.23.5", "end_time_seconds": "1699296949" }, "total": 473.451441181, "count": 1, "self": 0.8092994889999545, "children": { "run_training.setup": { "total": 0.08194277600000532, "count": 1, "self": 0.08194277600000532 }, "TrainerController.start_learning": { "total": 472.56019891600005, "count": 1, "self": 0.5820175900009872, "children": { "TrainerController._reset_env": { "total": 9.32639925899997, "count": 1, "self": 9.32639925899997 }, "TrainerController.advance": { "total": 462.5263529129991, "count": 18214, "self": 0.2996015039932445, "children": { "env_step": { "total": 462.22675140900583, "count": 18214, "self": 314.7471462939894, "children": { "SubprocessEnvManager._take_step": { "total": 147.17933570700836, "count": 18214, "self": 1.4887572770068118, "children": { "TorchPolicy.evaluate": { "total": 145.69057843000155, "count": 18214, "self": 145.69057843000155 } } }, "workers": { "total": 0.30026940800809143, "count": 18214, "self": 0.0, "children": { "worker_root": { "total": 471.26077072000004, "count": 18214, "is_parallel": true, "self": 230.23119953199767, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005268366999985119, "count": 1, "is_parallel": true, "self": 0.003917881000063517, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013504859999216023, "count": 10, "is_parallel": true, "self": 0.0013504859999216023 } } }, "UnityEnvironment.step": { "total": 0.060663981000004696, "count": 1, "is_parallel": true, "self": 0.0007097040000303423, "children": { "UnityEnvironment._generate_step_input": { "total": 0.000414137000007031, "count": 1, "is_parallel": true, "self": 0.000414137000007031 }, "communicator.exchange": { "total": 0.0573851419999869, "count": 1, "is_parallel": true, "self": 0.0573851419999869 }, "steps_from_proto": { "total": 0.0021549979999804236, "count": 1, "is_parallel": true, "self": 0.00040528300002051765, "children": { "_process_rank_one_or_two_observation": { "total": 0.001749714999959906, "count": 10, "is_parallel": true, "self": 0.001749714999959906 } } } } } } }, "UnityEnvironment.step": { "total": 241.02957118800236, "count": 18213, "is_parallel": true, "self": 10.464401300013094, "children": { "UnityEnvironment._generate_step_input": { "total": 5.390758617985, "count": 18213, "is_parallel": true, "self": 5.390758617985 }, "communicator.exchange": { "total": 191.7239243070087, "count": 18213, "is_parallel": true, "self": 191.7239243070087 }, "steps_from_proto": { "total": 33.45048696299557, "count": 18213, "is_parallel": true, "self": 6.2477287729957425, "children": { "_process_rank_one_or_two_observation": { "total": 27.202758189999827, "count": 182130, "is_parallel": true, "self": 27.202758189999827 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00014493499998025072, "count": 1, "self": 0.00014493499998025072, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 458.8008963170335, "count": 476656, "is_parallel": true, "self": 10.026568959016117, "children": { "process_trajectory": { "total": 259.84732594001724, "count": 476656, "is_parallel": true, "self": 258.8630914140172, "children": { "RLTrainer._checkpoint": { "total": 0.9842345260000229, "count": 4, "is_parallel": true, "self": 0.9842345260000229 } } }, "_update_policy": { "total": 188.92700141800015, "count": 90, "is_parallel": true, "self": 55.98634485499957, "children": { "TorchPPOOptimizer.update": { "total": 132.94065656300057, "count": 4587, "is_parallel": true, "self": 132.94065656300057 } } } } } } } } }, "TrainerController._save_models": { "total": 0.1252842190000365, "count": 1, "self": 0.0011265010000442999, "children": { "RLTrainer._checkpoint": { "total": 0.1241577179999922, "count": 1, "self": 0.1241577179999922 } } } } } } }