{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9986068606376648, "min": 0.9986068606376648, "max": 2.8662350177764893, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9534.6982421875, "min": 9534.6982421875, "max": 29353.11328125, "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": 12.936360359191895, "min": 0.2383900284767151, "max": 12.936360359191895, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2522.59033203125, "min": 46.24766540527344, "max": 2630.3349609375, "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": 0.06807265696539509, "min": 0.06395963183447248, "max": 0.07404430099105572, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.27229062786158037, "min": 0.2558385273378899, "max": 0.3702215049552786, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.21502209235640135, "min": 0.11522623703942872, "max": 0.2751835286032919, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8600883694256054, "min": 0.4609049481577149, "max": 1.3759176430164597, "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": 25.022727272727273, "min": 3.159090909090909, "max": 25.78181818181818, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1101.0, "min": 139.0, "max": 1418.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.022727272727273, "min": 3.159090909090909, "max": 25.78181818181818, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1101.0, "min": 139.0, "max": 1418.0, "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": "1679707659", "python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \n[GCC 9.4.0]", "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": "1679708149" }, "total": 489.63528336599995, "count": 1, "self": 0.4359577420000278, "children": { "run_training.setup": { "total": 0.1083099230000073, "count": 1, "self": 0.1083099230000073 }, "TrainerController.start_learning": { "total": 489.09101570099995, "count": 1, "self": 0.5567878319978945, "children": { "TrainerController._reset_env": { "total": 9.563767720000016, "count": 1, "self": 9.563767720000016 }, "TrainerController.advance": { "total": 478.83743598300197, "count": 18202, "self": 0.3000923839979919, "children": { "env_step": { "total": 478.537343599004, "count": 18202, "self": 346.9129760940015, "children": { "SubprocessEnvManager._take_step": { "total": 131.3409756290017, "count": 18202, "self": 2.2995604460004415, "children": { "TorchPolicy.evaluate": { "total": 129.04141518300125, "count": 18202, "self": 129.04141518300125 } } }, "workers": { "total": 0.28339187600076343, "count": 18202, "self": 0.0, "children": { "worker_root": { "total": 487.5418107980006, "count": 18202, "is_parallel": true, "self": 234.66959943199672, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005248058000006495, "count": 1, "is_parallel": true, "self": 0.0038021860000299057, "children": { "_process_rank_one_or_two_observation": { "total": 0.001445871999976589, "count": 10, "is_parallel": true, "self": 0.001445871999976589 } } }, "UnityEnvironment.step": { "total": 0.04970447400000921, "count": 1, "is_parallel": true, "self": 0.000596395000030725, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003500229999815474, "count": 1, "is_parallel": true, "self": 0.0003500229999815474 }, "communicator.exchange": { "total": 0.04661340300000916, "count": 1, "is_parallel": true, "self": 0.04661340300000916 }, "steps_from_proto": { "total": 0.002144652999987784, "count": 1, "is_parallel": true, "self": 0.00041037899998741523, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017342740000003687, "count": 10, "is_parallel": true, "self": 0.0017342740000003687 } } } } } } }, "UnityEnvironment.step": { "total": 252.87221136600388, "count": 18201, "is_parallel": true, "self": 9.915767561998905, "children": { "UnityEnvironment._generate_step_input": { "total": 5.528890893004757, "count": 18201, "is_parallel": true, "self": 5.528890893004757 }, "communicator.exchange": { "total": 203.76743797099724, "count": 18201, "is_parallel": true, "self": 203.76743797099724 }, "steps_from_proto": { "total": 33.660114940002984, "count": 18201, "is_parallel": true, "self": 6.714385451008411, "children": { "_process_rank_one_or_two_observation": { "total": 26.945729488994573, "count": 182010, "is_parallel": true, "self": 26.945729488994573 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00011027200002899917, "count": 1, "self": 0.00011027200002899917, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 475.08528981797497, "count": 426500, "is_parallel": true, "self": 10.632348781991936, "children": { "process_trajectory": { "total": 264.23544279198336, "count": 426500, "is_parallel": true, "self": 262.65269028898337, "children": { "RLTrainer._checkpoint": { "total": 1.5827525029999947, "count": 4, "is_parallel": true, "self": 1.5827525029999947 } } }, "_update_policy": { "total": 200.21749824399964, "count": 90, "is_parallel": true, "self": 77.0879106100007, "children": { "TorchPPOOptimizer.update": { "total": 123.12958763399894, "count": 4587, "is_parallel": true, "self": 123.12958763399894 } } } } } } } } }, "TrainerController._save_models": { "total": 0.13291389400001208, "count": 1, "self": 0.000832610999964345, "children": { "RLTrainer._checkpoint": { "total": 0.13208128300004773, "count": 1, "self": 0.13208128300004773 } } } } } } }