{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.3299834430217743, "min": 0.3299834430217743, "max": 1.397074818611145, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 9910.0625, "min": 9910.0625, "max": 42381.66015625, "count": 33 }, "Pyramids.Step.mean": { "value": 989918.0, "min": 29952.0, "max": 989918.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989918.0, "min": 29952.0, "max": 989918.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.6386157274246216, "min": -0.10056138783693314, "max": 0.7230417132377625, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 178.81240844726562, "min": -23.833049774169922, "max": 207.51296997070312, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.002454492961987853, "min": -0.015735723078250885, "max": 0.571654200553894, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 0.6872580051422119, "min": -4.374530792236328, "max": 135.48204040527344, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06627447950276767, "min": 0.06537356437198782, "max": 0.07462056335657248, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9278427130387474, "min": 0.5223439434960073, "max": 1.095607174739616, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.016150521487274784, "min": 0.0005913565775541825, "max": 0.01618798502209904, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.22610730082184696, "min": 0.007096278930650189, "max": 0.2391700419447814, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.303426136985714e-06, "min": 7.303426136985714e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0001022479659178, "min": 0.0001022479659178, "max": 0.003507859730713499, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10243444285714286, "min": 0.10243444285714286, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4340822, "min": 1.3886848, "max": 2.5725911000000004, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002532008414285714, "min": 0.0002532008414285714, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0035448117799999996, "min": 0.0035448117799999996, "max": 0.11695172134999998, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.012964831665158272, "min": 0.012964831665158272, "max": 0.6129738092422485, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.1815076470375061, "min": 0.1815076470375061, "max": 4.290816783905029, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 292.5204081632653, "min": 276.9339622641509, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 28667.0, "min": 15984.0, "max": 32576.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.687063249854409, "min": -1.0000000521540642, "max": 1.7230660208272484, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 165.33219848573208, "min": -31.997201651334763, "max": 185.6449981033802, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.687063249854409, "min": -1.0000000521540642, "max": 1.7230660208272484, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 165.33219848573208, "min": -31.997201651334763, "max": 185.6449981033802, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.039251758312516635, "min": 0.039251758312516635, "max": 12.591468932107091, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.8466723146266304, "min": 3.8466723146266304, "max": 201.46350291371346, "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": "1719057322", "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": "2.3.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1719059710" }, "total": 2388.023172383, "count": 1, "self": 0.47694938499989803, "children": { "run_training.setup": { "total": 0.05359075199999097, "count": 1, "self": 0.05359075199999097 }, "TrainerController.start_learning": { "total": 2387.492632246, "count": 1, "self": 1.6344147980271373, "children": { "TrainerController._reset_env": { "total": 2.2439823389997855, "count": 1, "self": 2.2439823389997855 }, "TrainerController.advance": { "total": 2383.528367343973, "count": 64225, "self": 1.606426421929882, "children": { "env_step": { "total": 1733.1114603969947, "count": 64225, "self": 1589.590318909964, "children": { "SubprocessEnvManager._take_step": { "total": 142.57170619704766, "count": 64225, "self": 5.3295372460838735, "children": { "TorchPolicy.evaluate": { "total": 137.2421689509638, "count": 62560, "self": 137.2421689509638 } } }, "workers": { "total": 0.9494352899830574, "count": 64225, "self": 0.0, "children": { "worker_root": { "total": 2381.6972429809693, "count": 64225, "is_parallel": true, "self": 925.7478003609847, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002424538000013854, "count": 1, "is_parallel": true, "self": 0.0006949459998395469, "children": { "_process_rank_one_or_two_observation": { "total": 0.001729592000174307, "count": 8, "is_parallel": true, "self": 0.001729592000174307 } } }, "UnityEnvironment.step": { "total": 0.046569866000027105, "count": 1, "is_parallel": true, "self": 0.0006483350000507926, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004682109999976092, "count": 1, "is_parallel": true, "self": 0.0004682109999976092 }, "communicator.exchange": { "total": 0.043830706000107966, "count": 1, "is_parallel": true, "self": 0.043830706000107966 }, "steps_from_proto": { "total": 0.0016226139998707367, "count": 1, "is_parallel": true, "self": 0.0003462530000888364, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012763609997819003, "count": 8, "is_parallel": true, "self": 0.0012763609997819003 } } } } } } }, "UnityEnvironment.step": { "total": 1455.9494426199847, "count": 64224, "is_parallel": true, "self": 35.38330291314469, "children": { "UnityEnvironment._generate_step_input": { "total": 24.725623187986457, "count": 64224, "is_parallel": true, "self": 24.725623187986457 }, "communicator.exchange": { "total": 1290.1247222759064, "count": 64224, "is_parallel": true, "self": 1290.1247222759064 }, "steps_from_proto": { "total": 105.71579424294714, "count": 64224, "is_parallel": true, "self": 22.15793492206376, "children": { "_process_rank_one_or_two_observation": { "total": 83.55785932088338, "count": 513792, "is_parallel": true, "self": 83.55785932088338 } } } } } } } } } } }, "trainer_advance": { "total": 648.8104805250487, "count": 64225, "self": 3.000563049106404, "children": { "process_trajectory": { "total": 138.3256401599424, "count": 64225, "self": 138.12387631694264, "children": { "RLTrainer._checkpoint": { "total": 0.20176384299975325, "count": 2, "self": 0.20176384299975325 } } }, "_update_policy": { "total": 507.48427731599986, "count": 454, "self": 299.2771240380591, "children": { "TorchPPOOptimizer.update": { "total": 208.20715327794073, "count": 22815, "self": 208.20715327794073 } } } } } } }, "trainer_threads": { "total": 8.679999154992402e-07, "count": 1, "self": 8.679999154992402e-07 }, "TrainerController._save_models": { "total": 0.08586689699995986, "count": 1, "self": 0.0012743060001412232, "children": { "RLTrainer._checkpoint": { "total": 0.08459259099981864, "count": 1, "self": 0.08459259099981864 } } } } } } }