{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.28862422704696655, "min": 0.2809407114982605, "max": 1.458817720413208, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 8718.7607421875, "min": 8396.755859375, "max": 44254.6953125, "count": 33 }, "Pyramids.Step.mean": { "value": 989979.0, "min": 29952.0, "max": 989979.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989979.0, "min": 29952.0, "max": 989979.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.6428382992744446, "min": -0.1246735230088234, "max": 0.6922614574432373, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 187.06594848632812, "min": -29.921646118164062, "max": 204.21713256835938, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.0584355965256691, "min": -0.0584355965256691, "max": 0.36038246750831604, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -17.004758834838867, "min": -17.004758834838867, "max": 85.41064453125, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07232823468179309, "min": 0.06399515392939754, "max": 0.07344965892289544, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.0125952855451033, "min": 0.4831459649451125, "max": 1.0581684298231266, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01843703271047811, "min": 0.00035251193287553286, "max": 0.01843703271047811, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2581184579466935, "min": 0.0038776312616308614, "max": 0.2674198506186561, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.290911855442855e-06, "min": 7.290911855442855e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010207276597619997, "min": 0.00010207276597619997, "max": 0.0035075285308239, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10243027142857142, "min": 0.10243027142857142, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4340237999999998, "min": 1.3691136000000002, "max": 2.5691761, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002527841157142857, "min": 0.0002527841157142857, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0035389776199999997, "min": 0.0035389776199999997, "max": 0.11694069238999999, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.014820600859820843, "min": 0.014006749726831913, "max": 0.3859264850616455, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.20748841762542725, "min": 0.19609449803829193, "max": 2.7014853954315186, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 283.14285714285717, "min": 263.0, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29730.0, "min": 15984.0, "max": 33511.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6977999842592648, "min": -1.0000000521540642, "max": 1.705538299317672, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 178.2689983472228, "min": -32.000001668930054, "max": 199.2277975603938, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6977999842592648, "min": -1.0000000521540642, "max": 1.705538299317672, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 178.2689983472228, "min": -32.000001668930054, "max": 199.2277975603938, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.0424466908097245, "min": 0.03876904785806218, "max": 7.426969877444208, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 4.456902535021072, "min": 4.250657819655316, "max": 118.83151803910732, "count": 33 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 33 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 33 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1737433903", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "command_line_arguments": "/home/hwting/anaconda3/envs/rl/bin/mlagents-learn ./PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.5.1+cu124", "numpy_version": "1.23.5", "end_time_seconds": "1737434959" }, "total": 1055.95550495, "count": 1, "self": 0.2685949490000894, "children": { "run_training.setup": { "total": 0.0180650689999311, "count": 1, "self": 0.0180650689999311 }, "TrainerController.start_learning": { "total": 1055.668844932, "count": 1, "self": 1.0982156619033958, "children": { "TrainerController._reset_env": { "total": 1.9043728050000936, "count": 1, "self": 1.9043728050000936 }, "TrainerController.advance": { "total": 1052.6131045560965, "count": 64166, "self": 1.0108046640084467, "children": { "env_step": { "total": 672.2785516520603, "count": 64166, "self": 567.2175785179611, "children": { "SubprocessEnvManager._take_step": { "total": 104.33052053400343, "count": 64166, "self": 2.758082715972705, "children": { "TorchPolicy.evaluate": { "total": 101.57243781803072, "count": 62551, "self": 101.57243781803072 } } }, "workers": { "total": 0.7304526000957594, "count": 64166, "self": 0.0, "children": { "worker_root": { "total": 1054.1844523800764, "count": 64166, "is_parallel": true, "self": 557.6570615759515, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.001119297000059305, "count": 1, "is_parallel": true, "self": 0.0003847510001833143, "children": { "_process_rank_one_or_two_observation": { "total": 0.0007345459998759907, "count": 8, "is_parallel": true, "self": 0.0007345459998759907 } } }, "UnityEnvironment.step": { "total": 0.022782076000112284, "count": 1, "is_parallel": true, "self": 0.0002180479996241047, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00020099700032005785, "count": 1, "is_parallel": true, "self": 0.00020099700032005785 }, "communicator.exchange": { "total": 0.021732799999881536, "count": 1, "is_parallel": true, "self": 0.021732799999881536 }, "steps_from_proto": { "total": 0.0006302310002865852, "count": 1, "is_parallel": true, "self": 0.0001604500007488241, "children": { "_process_rank_one_or_two_observation": { "total": 0.0004697809995377611, "count": 8, "is_parallel": true, "self": 0.0004697809995377611 } } } } } } }, "UnityEnvironment.step": { "total": 496.52739080412493, "count": 64165, "is_parallel": true, "self": 16.392972244128032, "children": { "UnityEnvironment._generate_step_input": { "total": 14.634547571996336, "count": 64165, "is_parallel": true, "self": 14.634547571996336 }, "communicator.exchange": { "total": 418.8773176940008, "count": 64165, "is_parallel": true, "self": 418.8773176940008 }, "steps_from_proto": { "total": 46.62255329399977, "count": 64165, "is_parallel": true, "self": 10.444303778785525, "children": { "_process_rank_one_or_two_observation": { "total": 36.17824951521425, "count": 513320, "is_parallel": true, "self": 36.17824951521425 } } } } } } } } } } }, "trainer_advance": { "total": 379.3237482400277, "count": 64166, "self": 2.148907209002118, "children": { "process_trajectory": { "total": 74.19425005702078, "count": 64166, "self": 74.07855239002038, "children": { "RLTrainer._checkpoint": { "total": 0.11569766700040418, "count": 2, "self": 0.11569766700040418 } } }, "_update_policy": { "total": 302.9805909740048, "count": 448, "self": 163.80654075699476, "children": { "TorchPPOOptimizer.update": { "total": 139.17405021701006, "count": 22863, "self": 139.17405021701006 } } } } } } }, "trainer_threads": { "total": 5.50999629922444e-07, "count": 1, "self": 5.50999629922444e-07 }, "TrainerController._save_models": { "total": 0.05315135800037751, "count": 1, "self": 0.0010079050002786971, "children": { "RLTrainer._checkpoint": { "total": 0.052143453000098816, "count": 1, "self": 0.052143453000098816 } } } } } } }