{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.45144903659820557, "min": 0.45144903659820557, "max": 1.4546117782592773, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 13745.720703125, "min": 13745.720703125, "max": 44127.1015625, "count": 33 }, "Pyramids.Step.mean": { "value": 989988.0, "min": 29884.0, "max": 989988.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989988.0, "min": 29884.0, "max": 989988.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.6039779782295227, "min": -0.09628661721944809, "max": 0.6039779782295227, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 169.71780395507812, "min": -23.301361083984375, "max": 169.71780395507812, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.005139841698110104, "min": -0.08753462880849838, "max": 0.346064954996109, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 1.4442955255508423, "min": -23.021608352661133, "max": 82.01739501953125, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06536575123793753, "min": 0.06248163894737706, "max": 0.07390628284460521, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9151205173311254, "min": 0.5912502627568417, "max": 1.0622652414900835, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.016031046216227755, "min": 0.0009810267452543167, "max": 0.020399413331820743, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.22443464702718854, "min": 0.012753347688306117, "max": 0.2855917866454904, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.454433229507141e-06, "min": 7.454433229507141e-06, "max": 0.00029484765171744996, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010436206521309998, "min": 0.00010436206521309998, "max": 0.0037583152472282994, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10248477857142858, "min": 0.10248477857142858, "max": 0.19828255, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4347869000000002, "min": 1.4347869000000002, "max": 2.6527716999999997, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025822937928571423, "min": 0.00025822937928571423, "max": 0.009828426745, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0036152113099999993, "min": 0.0036152113099999993, "max": 0.12529189283, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.011388683691620827, "min": 0.011295264586806297, "max": 0.4017273783683777, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.15944157540798187, "min": 0.15813370048999786, "max": 3.2138190269470215, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 328.6875, "min": 328.6875, "max": 985.4545454545455, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 31554.0, "min": 16427.0, "max": 32520.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6296291430480778, "min": -0.8651455051519654, "max": 1.6296291430480778, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 156.44439773261547, "min": -28.54980167001486, "max": 156.44439773261547, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6296291430480778, "min": -0.8651455051519654, "max": 1.6296291430480778, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 156.44439773261547, "min": -28.54980167001486, "max": 156.44439773261547, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.03866716907001925, "min": 0.03866716907001925, "max": 8.364002719521523, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.712048230721848, "min": 3.37108197924681, "max": 142.18804623186588, "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": "1723207239", "python_version": "3.10.12 (main, Jul 29 2024, 16:56:48) [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": "2.3.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1723210400" }, "total": 3160.5517131109996, "count": 1, "self": 1.2109581269996852, "children": { "run_training.setup": { "total": 0.07258396799988986, "count": 1, "self": 0.07258396799988986 }, "TrainerController.start_learning": { "total": 3159.268171016, "count": 1, "self": 2.290939556037756, "children": { "TrainerController._reset_env": { "total": 2.7976361920000272, "count": 1, "self": 2.7976361920000272 }, "TrainerController.advance": { "total": 3154.037110499962, "count": 63871, "self": 2.5156189199628898, "children": { "env_step": { "total": 2084.224529412035, "count": 63871, "self": 1925.2744642960593, "children": { "SubprocessEnvManager._take_step": { "total": 157.50782159802475, "count": 63871, "self": 6.755935075946127, "children": { "TorchPolicy.evaluate": { "total": 150.75188652207862, "count": 62560, "self": 150.75188652207862 } } }, "workers": { "total": 1.4422435179508284, "count": 63871, "self": 0.0, "children": { "worker_root": { "total": 3152.0467003880594, "count": 63871, "is_parallel": true, "self": 1409.376671536097, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.00355952600011733, "count": 1, "is_parallel": true, "self": 0.0012517239997578145, "children": { "_process_rank_one_or_two_observation": { "total": 0.0023078020003595157, "count": 8, "is_parallel": true, "self": 0.0023078020003595157 } } }, "UnityEnvironment.step": { "total": 0.05978297699994073, "count": 1, "is_parallel": true, "self": 0.0007492470003853668, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005471760000546055, "count": 1, "is_parallel": true, "self": 0.0005471760000546055 }, "communicator.exchange": { "total": 0.05637916499972562, "count": 1, "is_parallel": true, "self": 0.05637916499972562 }, "steps_from_proto": { "total": 0.0021073889997751394, "count": 1, "is_parallel": true, "self": 0.0005085769998913747, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015988119998837647, "count": 8, "is_parallel": true, "self": 0.0015988119998837647 } } } } } } }, "UnityEnvironment.step": { "total": 1742.6700288519623, "count": 63870, "is_parallel": true, "self": 49.41027024292953, "children": { "UnityEnvironment._generate_step_input": { "total": 30.63422101601691, "count": 63870, "is_parallel": true, "self": 30.63422101601691 }, "communicator.exchange": { "total": 1533.6358760640073, "count": 63870, "is_parallel": true, "self": 1533.6358760640073 }, "steps_from_proto": { "total": 128.98966152900857, "count": 63870, "is_parallel": true, "self": 27.730346447383, "children": { "_process_rank_one_or_two_observation": { "total": 101.25931508162557, "count": 510960, "is_parallel": true, "self": 101.25931508162557 } } } } } } } } } } }, "trainer_advance": { "total": 1067.2969621679645, "count": 63871, "self": 4.595349156002612, "children": { "process_trajectory": { "total": 165.17038859495642, "count": 63871, "self": 164.81954804395673, "children": { "RLTrainer._checkpoint": { "total": 0.3508405509996919, "count": 2, "self": 0.3508405509996919 } } }, "_update_policy": { "total": 897.5312244170054, "count": 456, "self": 372.36562696301235, "children": { "TorchPPOOptimizer.update": { "total": 525.1655974539931, "count": 22827, "self": 525.1655974539931 } } } } } } }, "trainer_threads": { "total": 1.4590004866477102e-06, "count": 1, "self": 1.4590004866477102e-06 }, "TrainerController._save_models": { "total": 0.14248330899954453, "count": 1, "self": 0.00548895999963861, "children": { "RLTrainer._checkpoint": { "total": 0.13699434899990592, "count": 1, "self": 0.13699434899990592 } } } } } } }