{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.17317955195903778, "min": 0.14168494939804077, "max": 1.4583802223205566, "count": 100 }, "Pyramids.Policy.Entropy.sum": { "value": 5175.990234375, "min": 4232.41259765625, "max": 44241.421875, "count": 100 }, "Pyramids.Step.mean": { "value": 2999875.0, "min": 29874.0, "max": 2999875.0, "count": 100 }, "Pyramids.Step.sum": { "value": 2999875.0, "min": 29874.0, "max": 2999875.0, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.7691124081611633, "min": -0.08535858243703842, "max": 0.9041013121604919, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 228.4263916015625, "min": -20.656776428222656, "max": 279.3673095703125, "count": 100 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.0017214497784152627, "min": -0.04016052186489105, "max": 0.3336523771286011, "count": 100 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -0.5112705826759338, "min": -11.36542797088623, "max": 79.07561492919922, "count": 100 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06405361736128497, "min": 0.062421531438465336, "max": 0.07488477575580844, "count": 100 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.8967506430579896, "min": 0.5241934302906591, "max": 1.0875261886851115, "count": 100 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.013071311008208842, "min": 0.0011910840556019593, "max": 0.017487810352920654, "count": 100 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.1829983541149238, "min": 0.01667517677842743, "max": 0.26231715529380983, "count": 100 }, "Pyramids.Policy.LearningRate.mean": { "value": 1.4529852299904792e-06, "min": 1.4529852299904792e-06, "max": 0.00029838354339596195, "count": 100 }, "Pyramids.Policy.LearningRate.sum": { "value": 2.034179321986671e-05, "min": 2.034179321986671e-05, "max": 0.004072542942485734, "count": 100 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10048429523809524, "min": 0.10048429523809524, "max": 0.19946118095238097, "count": 100 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4067801333333334, "min": 1.3962282666666668, "max": 2.8575142666666666, "count": 100 }, "Pyramids.Policy.Beta.mean": { "value": 5.838109428571442e-05, "min": 5.838109428571442e-05, "max": 0.009946171977142856, "count": 100 }, "Pyramids.Policy.Beta.sum": { "value": 0.0008173353200000018, "min": 0.0008173353200000018, "max": 0.13576567524, "count": 100 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.006854945328086615, "min": 0.006854945328086615, "max": 0.37250733375549316, "count": 100 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.09596923738718033, "min": 0.09596923738718033, "max": 2.607551336288452, "count": 100 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 239.85714285714286, "min": 196.68493150684932, "max": 996.3548387096774, "count": 100 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30222.0, "min": 16801.0, "max": 33575.0, "count": 100 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6966317290114978, "min": -0.9327806977014388, "max": 1.801979438286938, "count": 100 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 213.77559785544872, "min": -28.916201628744602, "max": 263.31199853122234, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6966317290114978, "min": -0.9327806977014388, "max": 1.801979438286938, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 213.77559785544872, "min": -28.916201628744602, "max": 263.31199853122234, "count": 100 }, "Pyramids.Policy.RndReward.mean": { "value": 0.017045541508455893, "min": 0.015405026443376896, "max": 7.425769460551879, "count": 100 }, "Pyramids.Policy.RndReward.sum": { "value": 2.1477382300654426, "min": 2.135223191431578, "max": 126.23808082938194, "count": 100 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 100 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 100 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1680071811", "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/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": "1680084796" }, "total": 12984.881335327, "count": 1, "self": 1.1708516319995397, "children": { "run_training.setup": { "total": 0.15179159099994877, "count": 1, "self": 0.15179159099994877 }, "TrainerController.start_learning": { "total": 12983.558692104, "count": 1, "self": 8.476519966723572, "children": { "TrainerController._reset_env": { "total": 9.413040615, "count": 1, "self": 9.413040615 }, "TrainerController.advance": { "total": 12965.538337878275, "count": 195810, "self": 9.517743442527717, "children": { "env_step": { "total": 9196.753749088854, "count": 195810, "self": 8695.183518876203, "children": { "SubprocessEnvManager._take_step": { "total": 496.44982640273605, "count": 195810, "self": 26.284452152038966, "children": { "TorchPolicy.evaluate": { "total": 470.1653742506971, "count": 187557, "self": 470.1653742506971 } } }, "workers": { "total": 5.120403809914649, "count": 195810, "self": 0.0, "children": { "worker_root": { "total": 12954.305169195157, "count": 195810, "is_parallel": true, "self": 4920.182070330404, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.008985370000004878, "count": 1, "is_parallel": true, "self": 0.006744258000026093, "children": { "_process_rank_one_or_two_observation": { "total": 0.0022411119999787843, "count": 8, "is_parallel": true, "self": 0.0022411119999787843 } } }, "UnityEnvironment.step": { "total": 0.18531246200001306, "count": 1, "is_parallel": true, "self": 0.0007343249999394175, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0006194980000486794, "count": 1, "is_parallel": true, "self": 0.0006194980000486794 }, "communicator.exchange": { "total": 0.18170476300002747, "count": 1, "is_parallel": true, "self": 0.18170476300002747 }, "steps_from_proto": { "total": 0.00225387599999749, "count": 1, "is_parallel": true, "self": 0.0006706610000151159, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015832149999823741, "count": 8, "is_parallel": true, "self": 0.0015832149999823741 } } } } } } }, "UnityEnvironment.step": { "total": 8034.123098864753, "count": 195809, "is_parallel": true, "self": 155.28302885531502, "children": { "UnityEnvironment._generate_step_input": { "total": 89.27385179770596, "count": 195809, "is_parallel": true, "self": 89.27385179770596 }, "communicator.exchange": { "total": 7352.469061182791, "count": 195809, "is_parallel": true, "self": 7352.469061182791 }, "steps_from_proto": { "total": 437.0971570289413, "count": 195809, "is_parallel": true, "self": 102.84897756022781, "children": { "_process_rank_one_or_two_observation": { "total": 334.2481794687135, "count": 1566472, "is_parallel": true, "self": 334.2481794687135 } } } } } } } } } } }, "trainer_advance": { "total": 3759.266845346893, "count": 195810, "self": 17.724248950800757, "children": { "process_trajectory": { "total": 578.618079360096, "count": 195810, "self": 577.6141527380954, "children": { "RLTrainer._checkpoint": { "total": 1.003926622000563, "count": 6, "self": 1.003926622000563 } } }, "_update_policy": { "total": 3162.9245170359964, "count": 1403, "self": 1333.522691153, "children": { "TorchPPOOptimizer.update": { "total": 1829.4018258829963, "count": 68391, "self": 1829.4018258829963 } } } } } } }, "trainer_threads": { "total": 1.263000740436837e-06, "count": 1, "self": 1.263000740436837e-06 }, "TrainerController._save_models": { "total": 0.13079238099999202, "count": 1, "self": 0.002961570999104879, "children": { "RLTrainer._checkpoint": { "total": 0.12783081000088714, "count": 1, "self": 0.12783081000088714 } } } } } } }