{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.4581536650657654, "min": 0.44719448685646057, "max": 1.51397705078125, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 13656.64453125, "min": 13365.7490234375, "max": 45928.0078125, "count": 33 }, "Pyramids.Step.mean": { "value": 989898.0, "min": 29952.0, "max": 989898.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989898.0, "min": 29952.0, "max": 989898.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.3924131393432617, "min": -0.13667812943458557, "max": 0.47008126974105835, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 104.38189697265625, "min": -32.39271545410156, "max": 129.742431640625, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.020997608080506325, "min": -0.058555684983730316, "max": 0.22169116139411926, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 5.585363864898682, "min": -15.868590354919434, "max": 53.20587921142578, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07214341344359443, "min": 0.06603306579499452, "max": 0.0729378174164095, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.010007788210322, "min": 0.4943184620053802, "max": 1.0940672612461426, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.017572773998530345, "min": 0.0010463356599991855, "max": 0.017572773998530345, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2460188359794248, "min": 0.007324349619994299, "max": 0.2460188359794248, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.390340393728568e-06, "min": 7.390340393728568e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010346476551219996, "min": 0.00010346476551219996, "max": 0.003632312889229099, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10246341428571427, "min": 0.10246341428571427, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4344877999999999, "min": 1.3691136000000002, "max": 2.6107709000000003, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002560950871428571, "min": 0.0002560950871428571, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003585331219999999, "min": 0.003585331219999999, "max": 0.12109601291000001, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.010142854414880276, "min": 0.009317404590547085, "max": 0.31090760231018066, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.1419999599456787, "min": 0.13044366240501404, "max": 2.1763532161712646, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 424.5072463768116, "min": 386.2894736842105, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29291.0, "min": 15984.0, "max": 32807.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.368711739011547, "min": -1.0000000521540642, "max": 1.4820920889706988, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 93.0723982527852, "min": -32.000001668930054, "max": 112.63899876177311, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.368711739011547, "min": -1.0000000521540642, "max": 1.4820920889706988, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 93.0723982527852, "min": -32.000001668930054, "max": 112.63899876177311, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.04563360810789163, "min": 0.03726900073486736, "max": 5.921289462596178, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.103085351336631, "min": 2.832444055849919, "max": 94.74063140153885, "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": "1739225043", "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": "2.6.0+cu124", "numpy_version": "1.23.5", "end_time_seconds": "1739227201" }, "total": 2158.689573137, "count": 1, "self": 0.49150286100029916, "children": { "run_training.setup": { "total": 0.02156142000012551, "count": 1, "self": 0.02156142000012551 }, "TrainerController.start_learning": { "total": 2158.1765088559996, "count": 1, "self": 1.199628883033256, "children": { "TrainerController._reset_env": { "total": 2.222767715000373, "count": 1, "self": 2.222767715000373 }, "TrainerController.advance": { "total": 2154.668971563966, "count": 63629, "self": 1.2527238958159614, "children": { "env_step": { "total": 1480.5342529020313, "count": 63629, "self": 1334.495664945242, "children": { "SubprocessEnvManager._take_step": { "total": 145.33209973895782, "count": 63629, "self": 4.399872893911379, "children": { "TorchPolicy.evaluate": { "total": 140.93222684504644, "count": 62561, "self": 140.93222684504644 } } }, "workers": { "total": 0.7064882178315202, "count": 63629, "self": 0.0, "children": { "worker_root": { "total": 2153.554883463049, "count": 63629, "is_parallel": true, "self": 924.227458496046, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.001963775000149326, "count": 1, "is_parallel": true, "self": 0.0006409160005205194, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013228589996288065, "count": 8, "is_parallel": true, "self": 0.0013228589996288065 } } }, "UnityEnvironment.step": { "total": 0.049113237999790726, "count": 1, "is_parallel": true, "self": 0.0005659319999722356, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00042169400012426195, "count": 1, "is_parallel": true, "self": 0.00042169400012426195 }, "communicator.exchange": { "total": 0.04648125399990022, "count": 1, "is_parallel": true, "self": 0.04648125399990022 }, "steps_from_proto": { "total": 0.0016443579997940105, "count": 1, "is_parallel": true, "self": 0.0003616779986259644, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012826800011680461, "count": 8, "is_parallel": true, "self": 0.0012826800011680461 } } } } } } }, "UnityEnvironment.step": { "total": 1229.327424967003, "count": 63628, "is_parallel": true, "self": 30.61747447900825, "children": { "UnityEnvironment._generate_step_input": { "total": 22.591519865916325, "count": 63628, "is_parallel": true, "self": 22.591519865916325 }, "communicator.exchange": { "total": 1084.9353530800254, "count": 63628, "is_parallel": true, "self": 1084.9353530800254 }, "steps_from_proto": { "total": 91.18307754205307, "count": 63628, "is_parallel": true, "self": 17.609873982247336, "children": { "_process_rank_one_or_two_observation": { "total": 73.57320355980573, "count": 509024, "is_parallel": true, "self": 73.57320355980573 } } } } } } } } } } }, "trainer_advance": { "total": 672.8819947661186, "count": 63629, "self": 2.3793804801644, "children": { "process_trajectory": { "total": 123.29159027795276, "count": 63629, "self": 122.99580609095256, "children": { "RLTrainer._checkpoint": { "total": 0.2957841870002085, "count": 2, "self": 0.2957841870002085 } } }, "_update_policy": { "total": 547.2110240080015, "count": 449, "self": 301.27905448399315, "children": { "TorchPPOOptimizer.update": { "total": 245.9319695240083, "count": 22794, "self": 245.9319695240083 } } } } } } }, "trainer_threads": { "total": 8.759998308960348e-07, "count": 1, "self": 8.759998308960348e-07 }, "TrainerController._save_models": { "total": 0.0851398180002434, "count": 1, "self": 0.0012763089998770738, "children": { "RLTrainer._checkpoint": { "total": 0.08386350900036632, "count": 1, "self": 0.08386350900036632 } } } } } } }