{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.19784528017044067, "min": 0.18991874158382416, "max": 1.4398733377456665, "count": 100 }, "Pyramids.Policy.Entropy.sum": { "value": 6017.662109375, "min": 5685.4072265625, "max": 43679.99609375, "count": 100 }, "Pyramids.Step.mean": { "value": 2999958.0, "min": 29958.0, "max": 2999958.0, "count": 100 }, "Pyramids.Step.sum": { "value": 2999958.0, "min": 29958.0, "max": 2999958.0, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.7973716259002686, "min": -0.10952480137348175, "max": 0.8772773742675781, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 238.41412353515625, "min": -26.395477294921875, "max": 271.95599365234375, "count": 100 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.013140634633600712, "min": -0.05299131199717522, "max": 0.4938938021659851, "count": 100 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 3.9290497303009033, "min": -14.837567329406738, "max": 117.54672241210938, "count": 100 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07000825442461799, "min": 0.06275531533790533, "max": 0.07310722693052542, "count": 100 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9801155619446518, "min": 0.5023535676752137, "max": 1.0878443158455375, "count": 100 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.014094605516490373, "min": 0.00015380242119230456, "max": 0.016221997436756893, "count": 100 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.19732447723086521, "min": 0.001999431475499959, "max": 0.2433299615513534, "count": 100 }, "Pyramids.Policy.LearningRate.mean": { "value": 1.4372638066595227e-06, "min": 1.4372638066595227e-06, "max": 0.00029838354339596195, "count": 100 }, "Pyramids.Policy.LearningRate.sum": { "value": 2.0121693293233318e-05, "min": 2.0121693293233318e-05, "max": 0.0037596776467741662, "count": 100 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10047905476190477, "min": 0.10047905476190477, "max": 0.19946118095238097, "count": 100 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4067067666666668, "min": 1.3962282666666668, "max": 2.7376043666666665, "count": 100 }, "Pyramids.Policy.Beta.mean": { "value": 5.78575707142857e-05, "min": 5.78575707142857e-05, "max": 0.009946171977142856, "count": 100 }, "Pyramids.Policy.Beta.sum": { "value": 0.0008100059899999998, "min": 0.0008100059899999998, "max": 0.12533726075, "count": 100 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.005321188364177942, "min": 0.005321188364177942, "max": 0.39045023918151855, "count": 100 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.07449663430452347, "min": 0.07449663430452347, "max": 2.73315167427063, "count": 100 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 224.92248062015503, "min": 203.15714285714284, "max": 999.0, "count": 100 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29015.0, "min": 17652.0, "max": 32490.0, "count": 100 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.7750775059757307, "min": -0.9999467184146246, "max": 1.7968936008764498, "count": 100 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 228.98499827086926, "min": -31.992801621556282, "max": 253.3619977235794, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.7750775059757307, "min": -0.9999467184146246, "max": 1.7968936008764498, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 228.98499827086926, "min": -31.992801621556282, "max": 253.3619977235794, "count": 100 }, "Pyramids.Policy.RndReward.mean": { "value": 0.012639617834680365, "min": 0.012044258222008886, "max": 6.420608460903168, "count": 100 }, "Pyramids.Policy.RndReward.sum": { "value": 1.6305107006737671, "min": 1.597696806260501, "max": 115.57095229625702, "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": "1766767225", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "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": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.8.0+cu128", "numpy_version": "1.23.5", "end_time_seconds": "1766774488" }, "total": 7262.578842348, "count": 1, "self": 0.7331610630017167, "children": { "run_training.setup": { "total": 0.02270032699971125, "count": 1, "self": 0.02270032699971125 }, "TrainerController.start_learning": { "total": 7261.822980957999, "count": 1, "self": 4.362720833675667, "children": { "TrainerController._reset_env": { "total": 2.44654730000002, "count": 1, "self": 2.44654730000002 }, "TrainerController.advance": { "total": 7254.890186789323, "count": 195488, "self": 4.5691111893347625, "children": { "env_step": { "total": 5275.689085334836, "count": 195488, "self": 4820.37328167618, "children": { "SubprocessEnvManager._take_step": { "total": 452.65308636580676, "count": 195488, "self": 14.00063239111023, "children": { "TorchPolicy.evaluate": { "total": 438.6524539746965, "count": 187574, "self": 438.6524539746965 } } }, "workers": { "total": 2.6627172928492655, "count": 195488, "self": 0.0, "children": { "worker_root": { "total": 7241.459293001311, "count": 195488, "is_parallel": true, "self": 2781.8067687173625, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0017721609997352061, "count": 1, "is_parallel": true, "self": 0.0005518779989870382, "children": { "_process_rank_one_or_two_observation": { "total": 0.001220283000748168, "count": 8, "is_parallel": true, "self": 0.001220283000748168 } } }, "UnityEnvironment.step": { "total": 0.08760353199977544, "count": 1, "is_parallel": true, "self": 0.0005260439997982758, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004468950000955374, "count": 1, "is_parallel": true, "self": 0.0004468950000955374 }, "communicator.exchange": { "total": 0.08298599499994452, "count": 1, "is_parallel": true, "self": 0.08298599499994452 }, "steps_from_proto": { "total": 0.0036445979999371048, "count": 1, "is_parallel": true, "self": 0.00033002000009219046, "children": { "_process_rank_one_or_two_observation": { "total": 0.0033145779998449143, "count": 8, "is_parallel": true, "self": 0.0033145779998449143 } } } } } } }, "UnityEnvironment.step": { "total": 4459.652524283949, "count": 195487, "is_parallel": true, "self": 102.0019524152558, "children": { "UnityEnvironment._generate_step_input": { "total": 67.93321991408902, "count": 195487, "is_parallel": true, "self": 67.93321991408902 }, "communicator.exchange": { "total": 3974.1225162467676, "count": 195487, "is_parallel": true, "self": 3974.1225162467676 }, "steps_from_proto": { "total": 315.59483570783686, "count": 195487, "is_parallel": true, "self": 67.31909217636257, "children": { "_process_rank_one_or_two_observation": { "total": 248.2757435314743, "count": 1563896, "is_parallel": true, "self": 248.2757435314743 } } } } } } } } } } }, "trainer_advance": { "total": 1974.6319902651521, "count": 195488, "self": 9.088429786300821, "children": { "process_trajectory": { "total": 378.24658305787216, "count": 195488, "self": 377.6639317788731, "children": { "RLTrainer._checkpoint": { "total": 0.5826512789990375, "count": 6, "self": 0.5826512789990375 } } }, "_update_policy": { "total": 1587.2969774209791, "count": 1395, "self": 878.0354534816965, "children": { "TorchPPOOptimizer.update": { "total": 709.2615239392826, "count": 68343, "self": 709.2615239392826 } } } } } } }, "trainer_threads": { "total": 1.1590000212891027e-06, "count": 1, "self": 1.1590000212891027e-06 }, "TrainerController._save_models": { "total": 0.1235248760003742, "count": 1, "self": 0.001301593001699075, "children": { "RLTrainer._checkpoint": { "total": 0.12222328299867513, "count": 1, "self": 0.12222328299867513 } } } } } } }