{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 1.0121504068374634, "min": 0.9460815787315369, "max": 1.503366231918335, "count": 25 }, "Pyramids.Policy.Entropy.sum": { "value": 20032.48046875, "min": 19012.455078125, "max": 30211.6484375, "count": 25 }, "Pyramids.Step.mean": { "value": 499940.0, "min": 19968.0, "max": 499940.0, "count": 25 }, "Pyramids.Step.sum": { "value": 499940.0, "min": 19968.0, "max": 499940.0, "count": 25 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": -0.026038452982902527, "min": -0.11006768047809601, "max": 0.02244146727025509, "count": 25 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": -4.218229293823242, "min": -17.500761032104492, "max": 3.6355175971984863, "count": 25 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.01763242855668068, "min": 0.01425930019468069, "max": 0.3973273038864136, "count": 25 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 2.8564534187316895, "min": 2.2957472801208496, "max": 63.17504119873047, "count": 25 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06658720749889172, "min": 0.06285811453503008, "max": 0.07633348781014686, "count": 25 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.6658720749889171, "min": 0.2727794712516426, "max": 0.7160643609806877, "count": 25 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.003296598828339091, "min": 0.00021042404057236845, "max": 0.015986815926257333, "count": 25 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.03296598828339091, "min": 0.0017292712748508332, "max": 0.06394726370502933, "count": 25 }, "Pyramids.Policy.LearningRate.mean": { "value": 5.765018078360002e-06, "min": 5.765018078360002e-06, "max": 0.00029391360202879994, "count": 25 }, "Pyramids.Policy.LearningRate.sum": { "value": 5.765018078360002e-05, "min": 5.765018078360002e-05, "max": 0.0020648809117064, "count": 25 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10192164000000001, "min": 0.10192164000000001, "max": 0.1979712, "count": 25 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.0192164000000001, "min": 0.7918848, "max": 1.5669624, "count": 25 }, "Pyramids.Policy.Beta.mean": { "value": 0.00020197183600000014, "min": 0.00020197183600000014, "max": 0.009797322879999997, "count": 25 }, "Pyramids.Policy.Beta.sum": { "value": 0.0020197183600000014, "min": 0.0020197183600000014, "max": 0.06884053064, "count": 25 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.016766127198934555, "min": 0.016766127198934555, "max": 0.5906252861022949, "count": 25 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.16766127943992615, "min": 0.156918466091156, "max": 2.3625011444091797, "count": 25 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 902.0, "min": 835.1304347826087, "max": 999.0, "count": 25 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 19844.0, "min": 15631.0, "max": 30619.0, "count": 25 }, "Pyramids.Environment.CumulativeReward.mean": { "value": -0.44795459136366844, "min": -1.0000000521540642, "max": -0.1398783096152803, "count": 25 }, "Pyramids.Environment.CumulativeReward.sum": { "value": -9.855001010000706, "min": -28.64680152386427, "max": -3.2172011211514473, "count": 25 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": -0.44795459136366844, "min": -1.0000000521540642, "max": -0.1398783096152803, "count": 25 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": -9.855001010000706, "min": -28.64680152386427, "max": -3.2172011211514473, "count": 25 }, "Pyramids.Policy.RndReward.mean": { "value": 0.15901358330368318, "min": 0.14874269537951634, "max": 9.738041854463518, "count": 25 }, "Pyramids.Policy.RndReward.sum": { "value": 3.49829883268103, "min": 3.421081993728876, "max": 155.80866967141628, "count": 25 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 25 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 25 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1749532101", "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": "2.7.1+cu126", "numpy_version": "1.23.5", "end_time_seconds": "1749533204" }, "total": 1103.651244273, "count": 1, "self": 0.4777003239996702, "children": { "run_training.setup": { "total": 0.021289202999923873, "count": 1, "self": 0.021289202999923873 }, "TrainerController.start_learning": { "total": 1103.1522547460004, "count": 1, "self": 0.6987394619704901, "children": { "TrainerController._reset_env": { "total": 2.8920449060001374, "count": 1, "self": 2.8920449060001374 }, "TrainerController.advance": { "total": 1099.4652133230297, "count": 31560, "self": 0.7282170380190109, "children": { "env_step": { "total": 753.6990319060619, "count": 31560, "self": 673.6376814861242, "children": { "SubprocessEnvManager._take_step": { "total": 79.64410036299614, "count": 31560, "self": 2.4693943649881476, "children": { "TorchPolicy.evaluate": { "total": 77.174705998008, "count": 31306, "self": 77.174705998008 } } }, "workers": { "total": 0.41725005694161155, "count": 31560, "self": 0.0, "children": { "worker_root": { "total": 1100.3690120639862, "count": 31560, "is_parallel": true, "self": 486.0401613490021, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0020381109998197644, "count": 1, "is_parallel": true, "self": 0.0007387539990304504, "children": { "_process_rank_one_or_two_observation": { "total": 0.001299357000789314, "count": 8, "is_parallel": true, "self": 0.001299357000789314 } } }, "UnityEnvironment.step": { "total": 0.1065906100002394, "count": 1, "is_parallel": true, "self": 0.0005650740004057297, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004772229999616684, "count": 1, "is_parallel": true, "self": 0.0004772229999616684 }, "communicator.exchange": { "total": 0.10394590599980802, "count": 1, "is_parallel": true, "self": 0.10394590599980802 }, "steps_from_proto": { "total": 0.0016024070000639767, "count": 1, "is_parallel": true, "self": 0.00036290200068833656, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012395049993756402, "count": 8, "is_parallel": true, "self": 0.0012395049993756402 } } } } } } }, "UnityEnvironment.step": { "total": 614.3288507149841, "count": 31559, "is_parallel": true, "self": 16.558972978113616, "children": { "UnityEnvironment._generate_step_input": { "total": 12.415291498007264, "count": 31559, "is_parallel": true, "self": 12.415291498007264 }, "communicator.exchange": { "total": 533.5693294359462, "count": 31559, "is_parallel": true, "self": 533.5693294359462 }, "steps_from_proto": { "total": 51.78525680291705, "count": 31559, "is_parallel": true, "self": 10.327377288923799, "children": { "_process_rank_one_or_two_observation": { "total": 41.45787951399325, "count": 252472, "is_parallel": true, "self": 41.45787951399325 } } } } } } } } } } }, "trainer_advance": { "total": 345.0379643789488, "count": 31560, "self": 1.1553330019182795, "children": { "process_trajectory": { "total": 66.97376207703155, "count": 31560, "self": 66.8499179780315, "children": { "RLTrainer._checkpoint": { "total": 0.12384409900005267, "count": 1, "self": 0.12384409900005267 } } }, "_update_policy": { "total": 276.90886929999897, "count": 217, "self": 155.22698258899072, "children": { "TorchPPOOptimizer.update": { "total": 121.68188671100825, "count": 11439, "self": 121.68188671100825 } } } } } } }, "trainer_threads": { "total": 1.0869998732232489e-06, "count": 1, "self": 1.0869998732232489e-06 }, "TrainerController._save_models": { "total": 0.09625596800015046, "count": 1, "self": 0.0011127219995614723, "children": { "RLTrainer._checkpoint": { "total": 0.09514324600058899, "count": 1, "self": 0.09514324600058899 } } } } } } }