{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.17373692989349365, "min": 0.17373692989349365, "max": 1.3758944272994995, "count": 66 }, "Pyramids.Policy.Entropy.sum": { "value": 5198.208984375, "min": 5198.208984375, "max": 41739.1328125, "count": 66 }, "Pyramids.Step.mean": { "value": 1979980.0, "min": 29952.0, "max": 1979980.0, "count": 66 }, "Pyramids.Step.sum": { "value": 1979980.0, "min": 29952.0, "max": 1979980.0, "count": 66 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.635413646697998, "min": -0.1335158348083496, "max": 0.754490315914154, "count": 66 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 183.63455200195312, "min": -31.643251419067383, "max": 224.0836181640625, "count": 66 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.026545614004135132, "min": -0.026545614004135132, "max": 0.3384619951248169, "count": 66 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -7.671682357788086, "min": -7.671682357788086, "max": 81.23088073730469, "count": 66 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07079870276876526, "min": 0.06494210678774441, "max": 0.074074601904223, "count": 66 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9911818387627137, "min": 0.5058980644717358, "max": 1.0923488790285774, "count": 66 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.016418092344316564, "min": 8.354040726377123e-05, "max": 0.01651646321462839, "count": 66 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2298532928204319, "min": 0.0010860252944290259, "max": 0.23123048500479745, "count": 66 }, "Pyramids.Policy.LearningRate.mean": { "value": 5.292419664464287e-06, "min": 5.292419664464287e-06, "max": 0.0002975753150939428, "count": 66 }, "Pyramids.Policy.LearningRate.sum": { "value": 7.409387530250002e-05, "min": 7.409387530250002e-05, "max": 0.0038542138152620996, "count": 66 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10176410714285714, "min": 0.10176410714285714, "max": 0.19919177142857142, "count": 66 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4246975, "min": 1.3845568000000001, "max": 2.6847378999999996, "count": 66 }, "Pyramids.Policy.Beta.mean": { "value": 0.00018623430357142862, "min": 0.00018623430357142862, "max": 0.009919257965714285, "count": 66 }, "Pyramids.Policy.Beta.sum": { "value": 0.0026072802500000008, "min": 0.0026072802500000008, "max": 0.12848531621, "count": 66 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.006160723511129618, "min": 0.006160723511129618, "max": 0.5207392573356628, "count": 66 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.08625012636184692, "min": 0.08625012636184692, "max": 3.645174980163574, "count": 66 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 283.1588785046729, "min": 240.06451612903226, "max": 999.0, "count": 66 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30298.0, "min": 15984.0, "max": 32546.0, "count": 66 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6209433818903733, "min": -1.0000000521540642, "max": 1.6994749850460462, "count": 66 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 171.81999848037958, "min": -32.000001668930054, "max": 206.56999798119068, "count": 66 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6209433818903733, "min": -1.0000000521540642, "max": 1.6994749850460462, "count": 66 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 171.81999848037958, "min": -32.000001668930054, "max": 206.56999798119068, "count": 66 }, "Pyramids.Policy.RndReward.mean": { "value": 0.018635886011289363, "min": 0.016045073169965972, "max": 11.277974216267467, "count": 66 }, "Pyramids.Policy.RndReward.sum": { "value": 1.9754039171966724, "min": 1.9139632204169175, "max": 180.44758746027946, "count": 66 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 66 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 66 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1704285072", "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/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.1.2+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1704289746" }, "total": 4674.513625539001, "count": 1, "self": 0.47622775099989667, "children": { "run_training.setup": { "total": 0.04479778999984774, "count": 1, "self": 0.04479778999984774 }, "TrainerController.start_learning": { "total": 4673.9925999980005, "count": 1, "self": 2.796508376924976, "children": { "TrainerController._reset_env": { "total": 1.9941864420002275, "count": 1, "self": 1.9941864420002275 }, "TrainerController.advance": { "total": 4669.118257359076, "count": 128758, "self": 2.907245709813651, "children": { "env_step": { "total": 3409.169055159192, "count": 128758, "self": 3144.4008717635297, "children": { "SubprocessEnvManager._take_step": { "total": 263.0533501308046, "count": 128758, "self": 9.538687400170602, "children": { "TorchPolicy.evaluate": { "total": 253.51466273063397, "count": 125069, "self": 253.51466273063397 } } }, "workers": { "total": 1.7148332648575888, "count": 128758, "self": 0.0, "children": { "worker_root": { "total": 4663.443710433065, "count": 128758, "is_parallel": true, "self": 1766.4048526630718, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0017913430001499364, "count": 1, "is_parallel": true, "self": 0.0005767310003648163, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012146119997851201, "count": 8, "is_parallel": true, "self": 0.0012146119997851201 } } }, "UnityEnvironment.step": { "total": 0.05095136299996739, "count": 1, "is_parallel": true, "self": 0.0005931489999966288, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0006151210000098217, "count": 1, "is_parallel": true, "self": 0.0006151210000098217 }, "communicator.exchange": { "total": 0.04803507599990553, "count": 1, "is_parallel": true, "self": 0.04803507599990553 }, "steps_from_proto": { "total": 0.0017080170000554062, "count": 1, "is_parallel": true, "self": 0.0003813270004684455, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013266899995869608, "count": 8, "is_parallel": true, "self": 0.0013266899995869608 } } } } } } }, "UnityEnvironment.step": { "total": 2897.038857769993, "count": 128757, "is_parallel": true, "self": 70.29768440079215, "children": { "UnityEnvironment._generate_step_input": { "total": 50.65141788408073, "count": 128757, "is_parallel": true, "self": 50.65141788408073 }, "communicator.exchange": { "total": 2570.5614011689267, "count": 128757, "is_parallel": true, "self": 2570.5614011689267 }, "steps_from_proto": { "total": 205.52835431619314, "count": 128757, "is_parallel": true, "self": 41.52870652874162, "children": { "_process_rank_one_or_two_observation": { "total": 163.99964778745152, "count": 1030056, "is_parallel": true, "self": 163.99964778745152 } } } } } } } } } } }, "trainer_advance": { "total": 1257.0419564900699, "count": 128758, "self": 5.484660723111119, "children": { "process_trajectory": { "total": 261.0180609279432, "count": 128758, "self": 260.6346793619423, "children": { "RLTrainer._checkpoint": { "total": 0.383381566000935, "count": 4, "self": 0.383381566000935 } } }, "_update_policy": { "total": 990.5392348390155, "count": 917, "self": 586.9659766111072, "children": { "TorchPPOOptimizer.update": { "total": 403.57325822790835, "count": 45576, "self": 403.57325822790835 } } } } } } }, "trainer_threads": { "total": 8.869992598192766e-07, "count": 1, "self": 8.869992598192766e-07 }, "TrainerController._save_models": { "total": 0.08364693300063664, "count": 1, "self": 0.0014177950006342144, "children": { "RLTrainer._checkpoint": { "total": 0.08222913800000242, "count": 1, "self": 0.08222913800000242 } } } } } } }