{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.8009202480316162, "min": 0.7395164370536804, "max": 1.5082975625991821, "count": 14 }, "Pyramids.Policy.Entropy.sum": { "value": 23963.533203125, "min": 22239.3671875, "max": 45755.71484375, "count": 14 }, "Pyramids.Step.mean": { "value": 419926.0, "min": 29952.0, "max": 419926.0, "count": 14 }, "Pyramids.Step.sum": { "value": 419926.0, "min": 29952.0, "max": 419926.0, "count": 14 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.007818647660315037, "min": -0.011158403940498829, "max": 0.007818647660315037, "count": 14 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 1.9233874082565308, "min": -2.6445417404174805, "max": 1.9233874082565308, "count": 14 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.05570051074028015, "min": 0.04640258848667145, "max": 0.5477548241615295, "count": 14 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 13.702325820922852, "min": 11.275829315185547, "max": 129.81788635253906, "count": 14 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.050763980583204624, "min": 0.04681522059977324, "max": 0.05453468236254946, "count": 14 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.7106957281648647, "min": 0.36650751996369635, "max": 0.7207024861127138, "count": 14 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.0012189357651907682, "min": 0.00033678642998324904, "max": 0.009745490534534875, "count": 14 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.017065100712670755, "min": 0.004033944906528372, "max": 0.06821843374174413, "count": 14 }, "Pyramids.Policy.LearningRate.mean": { "value": 0.0002190358127023571, "min": 0.0002190358127023571, "max": 0.00029676708679192377, "count": 14 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0030665013778329994, "min": 0.0020382272205909328, "max": 0.0039150343949885995, "count": 14 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.17301192857142864, "min": 0.17301192857142864, "max": 0.19892236190476192, "count": 14 }, "Pyramids.Policy.Epsilon.sum": { "value": 2.422167000000001, "min": 1.3794090666666667, "max": 2.8050114000000006, "count": 14 }, "Pyramids.Policy.Beta.mean": { "value": 0.007303891664285715, "min": 0.007303891664285715, "max": 0.009892343954285714, "count": 14 }, "Pyramids.Policy.Beta.sum": { "value": 0.1022544833, "min": 0.06794296576, "max": 0.13052063885999998, "count": 14 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.033260494470596313, "min": 0.033260494470596313, "max": 0.7636728882789612, "count": 14 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.4656469225883484, "min": 0.4656469225883484, "max": 5.345710277557373, "count": 14 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 869.9411764705883, "min": 811.0, "max": 999.0, "count": 14 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29578.0, "min": 15984.0, "max": 32098.0, "count": 14 }, "Pyramids.Environment.CumulativeReward.mean": { "value": -0.16451180989251418, "min": -1.0000000521540642, "max": 0.10759996280476854, "count": 14 }, "Pyramids.Environment.CumulativeReward.sum": { "value": -5.593401536345482, "min": -32.000001668930054, "max": 3.981198623776436, "count": 14 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": -0.16451180989251418, "min": -1.0000000521540642, "max": 0.10759996280476854, "count": 14 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": -5.593401536345482, "min": -32.000001668930054, "max": 3.981198623776436, "count": 14 }, "Pyramids.Policy.RndReward.mean": { "value": 0.30343032596112396, "min": 0.30343032596112396, "max": 14.843034541234374, "count": 14 }, "Pyramids.Policy.RndReward.sum": { "value": 10.316631082678214, "min": 10.316631082678214, "max": 237.48855265974998, "count": 14 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 14 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 14 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1687952159", "python_version": "3.10.12 (main, Jun 7 2023, 12:45:35) [GCC 9.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids-Training --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": "1687953065" }, "total": 905.8644368479999, "count": 1, "self": 0.23412299599976905, "children": { "run_training.setup": { "total": 0.03994181300004129, "count": 1, "self": 0.03994181300004129 }, "TrainerController.start_learning": { "total": 905.590372039, "count": 1, "self": 0.5443300249787626, "children": { "TrainerController._reset_env": { "total": 5.302121001000046, "count": 1, "self": 5.302121001000046 }, "TrainerController.advance": { "total": 899.4936765480213, "count": 26748, "self": 0.5566726750208773, "children": { "env_step": { "total": 606.7365380339949, "count": 26748, "self": 553.2975351919897, "children": { "SubprocessEnvManager._take_step": { "total": 53.12541479800734, "count": 26748, "self": 1.9499418160000914, "children": { "TorchPolicy.evaluate": { "total": 51.17547298200725, "count": 26509, "self": 51.17547298200725 } } }, "workers": { "total": 0.31358804399781093, "count": 26747, "self": 0.0, "children": { "worker_root": { "total": 903.529167836978, "count": 26747, "is_parallel": true, "self": 395.44945059797385, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.001877981000006912, "count": 1, "is_parallel": true, "self": 0.0006266419999292339, "children": { "_process_rank_one_or_two_observation": { "total": 0.001251339000077678, "count": 8, "is_parallel": true, "self": 0.001251339000077678 } } }, "UnityEnvironment.step": { "total": 0.08084031099997446, "count": 1, "is_parallel": true, "self": 0.0005698239998537247, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005142130000876932, "count": 1, "is_parallel": true, "self": 0.0005142130000876932 }, "communicator.exchange": { "total": 0.07766689699997187, "count": 1, "is_parallel": true, "self": 0.07766689699997187 }, "steps_from_proto": { "total": 0.0020893770000611767, "count": 1, "is_parallel": true, "self": 0.00040608200015412876, "children": { "_process_rank_one_or_two_observation": { "total": 0.001683294999907048, "count": 8, "is_parallel": true, "self": 0.001683294999907048 } } } } } } }, "UnityEnvironment.step": { "total": 508.07971723900414, "count": 26746, "is_parallel": true, "self": 14.402299893028271, "children": { "UnityEnvironment._generate_step_input": { "total": 9.814417236978898, "count": 26746, "is_parallel": true, "self": 9.814417236978898 }, "communicator.exchange": { "total": 441.25282318099823, "count": 26746, "is_parallel": true, "self": 441.25282318099823 }, "steps_from_proto": { "total": 42.61017692799874, "count": 26746, "is_parallel": true, "self": 8.167402191992778, "children": { "_process_rank_one_or_two_observation": { "total": 34.44277473600596, "count": 213968, "is_parallel": true, "self": 34.44277473600596 } } } } } } } } } } }, "trainer_advance": { "total": 292.2004658390056, "count": 26747, "self": 0.9772115710293292, "children": { "process_trajectory": { "total": 51.72999506797498, "count": 26747, "self": 51.72999506797498 }, "_update_policy": { "total": 239.49325920000126, "count": 178, "self": 173.15960590700115, "children": { "TorchPPOOptimizer.update": { "total": 66.33365329300011, "count": 6392, "self": 66.33365329300011 } } } } } } }, "trainer_threads": { "total": 1.354000005449052e-06, "count": 1, "self": 1.354000005449052e-06 }, "TrainerController._save_models": { "total": 0.2502431109999179, "count": 1, "self": 0.0011992599997938669, "children": { "RLTrainer._checkpoint": { "total": 0.24904385100012405, "count": 1, "self": 0.24904385100012405 } } } } } } }