{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.5276034474372864, "min": 0.5203859210014343, "max": 1.4436898231506348, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 15912.51953125, "min": 15661.53515625, "max": 43795.7734375, "count": 33 }, "Pyramids.Step.mean": { "value": 989893.0, "min": 29952.0, "max": 989893.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989893.0, "min": 29952.0, "max": 989893.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.27893051505088806, "min": -0.11114157736301422, "max": 0.3688875734806061, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 71.12728118896484, "min": -26.340553283691406, "max": 95.54187774658203, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.7643086314201355, "min": -0.7643086314201355, "max": 0.2797998785972595, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -194.89869689941406, "min": -194.89869689941406, "max": 67.43177032470703, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06709537647655743, "min": 0.06473212007207087, "max": 0.07442723709725958, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.939335270671804, "min": 0.520990659680817, "max": 1.1135365502103047, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.1240374865477917, "min": 0.00011212205505846292, "max": 0.1240374865477917, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 1.736524811669084, "min": 0.0012333426056430922, "max": 1.736524811669084, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.430368951814288e-06, "min": 7.430368951814288e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010402516532540004, "min": 0.00010402516532540004, "max": 0.0031392260535913997, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10247675714285716, "min": 0.10247675714285716, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4346746000000001, "min": 1.3886848, "max": 2.3596462000000002, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025742803857142874, "min": 0.00025742803857142874, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003603992540000002, "min": 0.003603992540000002, "max": 0.10466621914, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.008705055341124535, "min": 0.008705055341124535, "max": 0.3740479052066803, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.12187077105045319, "min": 0.12187077105045319, "max": 2.618335247039795, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 563.3333333333334, "min": 476.58730158730157, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30420.0, "min": 15984.0, "max": 33513.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.0308836048299617, "min": -1.0000000521540642, "max": 1.3646158482583741, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 56.69859826564789, "min": -31.998801663517952, "max": 85.97079844027758, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.0308836048299617, "min": -1.0000000521540642, "max": 1.3646158482583741, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 56.69859826564789, "min": -31.998801663517952, "max": 85.97079844027758, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.05139069280650636, "min": 0.045106435728874725, "max": 7.483011702075601, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.82648810435785, "min": 2.5259604008169845, "max": 119.72818723320961, "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": "1681674753", "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": "1681676836" }, "total": 2082.4936676719994, "count": 1, "self": 0.5254055369991875, "children": { "run_training.setup": { "total": 0.11323993799987875, "count": 1, "self": 0.11323993799987875 }, "TrainerController.start_learning": { "total": 2081.8550221970004, "count": 1, "self": 1.5613643560477612, "children": { "TrainerController._reset_env": { "total": 4.303400775999762, "count": 1, "self": 4.303400775999762 }, "TrainerController.advance": { "total": 2075.8906668789523, "count": 63343, "self": 1.5118462648952118, "children": { "env_step": { "total": 1471.49027187606, "count": 63343, "self": 1360.4960932990343, "children": { "SubprocessEnvManager._take_step": { "total": 110.08357976691741, "count": 63343, "self": 4.8179702139127585, "children": { "TorchPolicy.evaluate": { "total": 105.26560955300465, "count": 62587, "self": 105.26560955300465 } } }, "workers": { "total": 0.9105988101082403, "count": 63343, "self": 0.0, "children": { "worker_root": { "total": 2076.912850426982, "count": 63343, "is_parallel": true, "self": 830.6232360530748, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0016617770002085308, "count": 1, "is_parallel": true, "self": 0.000501475999953982, "children": { "_process_rank_one_or_two_observation": { "total": 0.0011603010002545489, "count": 8, "is_parallel": true, "self": 0.0011603010002545489 } } }, "UnityEnvironment.step": { "total": 0.0910054040000432, "count": 1, "is_parallel": true, "self": 0.0005685990004167252, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00046193899970603525, "count": 1, "is_parallel": true, "self": 0.00046193899970603525 }, "communicator.exchange": { "total": 0.08746850399984396, "count": 1, "is_parallel": true, "self": 0.08746850399984396 }, "steps_from_proto": { "total": 0.0025063620000764786, "count": 1, "is_parallel": true, "self": 0.0011746469999707188, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013317150001057598, "count": 8, "is_parallel": true, "self": 0.0013317150001057598 } } } } } } }, "UnityEnvironment.step": { "total": 1246.2896143739072, "count": 63342, "is_parallel": true, "self": 32.388829574957526, "children": { "UnityEnvironment._generate_step_input": { "total": 22.64768769702914, "count": 63342, "is_parallel": true, "self": 22.64768769702914 }, "communicator.exchange": { "total": 1097.2017459979897, "count": 63342, "is_parallel": true, "self": 1097.2017459979897 }, "steps_from_proto": { "total": 94.05135110393076, "count": 63342, "is_parallel": true, "self": 19.99270235603217, "children": { "_process_rank_one_or_two_observation": { "total": 74.05864874789859, "count": 506736, "is_parallel": true, "self": 74.05864874789859 } } } } } } } } } } }, "trainer_advance": { "total": 602.8885487379971, "count": 63343, "self": 2.790356110146149, "children": { "process_trajectory": { "total": 102.40004174885507, "count": 63343, "self": 102.17514895185468, "children": { "RLTrainer._checkpoint": { "total": 0.22489279700039333, "count": 2, "self": 0.22489279700039333 } } }, "_update_policy": { "total": 497.6981508789959, "count": 440, "self": 317.04247819502507, "children": { "TorchPPOOptimizer.update": { "total": 180.6556726839708, "count": 22824, "self": 180.6556726839708 } } } } } } }, "trainer_threads": { "total": 1.0050007404061034e-06, "count": 1, "self": 1.0050007404061034e-06 }, "TrainerController._save_models": { "total": 0.09958918099982839, "count": 1, "self": 0.0015890380000200821, "children": { "RLTrainer._checkpoint": { "total": 0.0980001429998083, "count": 1, "self": 0.0980001429998083 } } } } } } }