{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.21312913298606873, "min": 0.21312913298606873, "max": 0.34789592027664185, "count": 30 }, "Pyramids.Policy.Entropy.sum": { "value": 6431.384765625, "min": 6431.384765625, "max": 10743.0263671875, "count": 30 }, "Pyramids.Step.mean": { "value": 2099875.0, "min": 1229959.0, "max": 2099875.0, "count": 30 }, "Pyramids.Step.sum": { "value": 2099875.0, "min": 1229959.0, "max": 2099875.0, "count": 30 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.7284514307975769, "min": 0.5540592074394226, "max": 0.7820839285850525, "count": 30 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 212.7078094482422, "min": 154.58251953125, "max": 235.40725708007812, "count": 30 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.00011148242629133165, "min": -0.036523718386888504, "max": 0.023824898526072502, "count": 30 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 0.032552868127822876, "min": -10.190117835998535, "max": 6.933045387268066, "count": 30 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 246.27272727272728, "min": 230.70247933884298, "max": 348.45054945054943, "count": 30 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29799.0, "min": 27384.0, "max": 31898.0, "count": 30 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.7371950270223224, "min": 1.5598866424626774, "max": 1.7692975122327648, "count": 30 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 210.200598269701, "min": 140.38979782164097, "max": 218.61299833655357, "count": 30 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.7371950270223224, "min": 1.5598866424626774, "max": 1.7692975122327648, "count": 30 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 210.200598269701, "min": 140.38979782164097, "max": 218.61299833655357, "count": 30 }, "Pyramids.Policy.RndReward.mean": { "value": 0.027385835378880088, "min": 0.026519934541434205, "max": 0.05033405645841008, "count": 30 }, "Pyramids.Policy.RndReward.sum": { "value": 3.313686080844491, "min": 3.2089120795135386, "max": 4.530065081256907, "count": 30 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07038099201536654, "min": 0.06557304179805419, "max": 0.07255525143340318, "count": 30 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9853338882151317, "min": 0.9180225851727586, "max": 1.0615770213286548, "count": 30 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.016201011241204624, "min": 0.012865025205568656, "max": 0.017286618631462466, "count": 30 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.22681415737686475, "min": 0.18011035287796118, "max": 0.259299279471937, "count": 30 }, "Pyramids.Policy.LearningRate.mean": { "value": 2.2603237363877542e-06, "min": 2.2603237363877542e-06, "max": 0.00012631876197539797, "count": 30 }, "Pyramids.Policy.LearningRate.sum": { "value": 3.164453230942856e-05, "min": 3.164453230942856e-05, "max": 0.0017684626676555716, "count": 30 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.1007534081632653, "min": 0.1007534081632653, "max": 0.1421062346938776, "count": 30 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4105477142857143, "min": 1.4105477142857143, "max": 2.067913761904762, "count": 30 }, "Pyramids.Policy.Beta.mean": { "value": 8.526547551020405e-05, "min": 8.526547551020405e-05, "max": 0.004216412845918367, "count": 30 }, "Pyramids.Policy.Beta.sum": { "value": 0.0011937166571428567, "min": 0.0011937166571428567, "max": 0.059029779842857136, "count": 30 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.01070969644933939, "min": 0.010628776624798775, "max": 0.014891265891492367, "count": 30 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.1499357521533966, "min": 0.14887894690036774, "max": 0.20847772061824799, "count": 30 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 30 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 30 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1767209721", "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 --resume", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.8.0+cu128", "numpy_version": "1.23.5", "end_time_seconds": "1767211999" }, "total": 2278.205391746, "count": 1, "self": 0.4811494629993831, "children": { "run_training.setup": { "total": 0.022436406000451825, "count": 1, "self": 0.022436406000451825 }, "TrainerController.start_learning": { "total": 2277.701805877, "count": 1, "self": 1.2841876258898992, "children": { "TrainerController._reset_env": { "total": 2.0473017460008123, "count": 1, "self": 2.0473017460008123 }, "TrainerController.advance": { "total": 2274.2910103411086, "count": 58898, "self": 1.3469239300684421, "children": { "env_step": { "total": 1689.9132824588696, "count": 58898, "self": 1557.947543781861, "children": { "SubprocessEnvManager._take_step": { "total": 131.1971453071019, "count": 58898, "self": 4.195159451937798, "children": { "TorchPolicy.evaluate": { "total": 127.0019858551641, "count": 56301, "self": 127.0019858551641 } } }, "workers": { "total": 0.7685933699067391, "count": 58898, "self": 0.0, "children": { "worker_root": { "total": 2271.9018152890612, "count": 58898, "is_parallel": true, "self": 822.0037834562008, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0018908930005636648, "count": 1, "is_parallel": true, "self": 0.0006353810003929539, "children": { "_process_rank_one_or_two_observation": { "total": 0.001255512000170711, "count": 8, "is_parallel": true, "self": 0.001255512000170711 } } }, "UnityEnvironment.step": { "total": 0.0512661869997828, "count": 1, "is_parallel": true, "self": 0.000529197998730524, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005153150004844065, "count": 1, "is_parallel": true, "self": 0.0005153150004844065 }, "communicator.exchange": { "total": 0.04860676699991018, "count": 1, "is_parallel": true, "self": 0.04860676699991018 }, "steps_from_proto": { "total": 0.0016149070006576949, "count": 1, "is_parallel": true, "self": 0.00032013300005928613, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012947740005984087, "count": 8, "is_parallel": true, "self": 0.0012947740005984087 } } } } } } }, "UnityEnvironment.step": { "total": 1449.8980318328604, "count": 58897, "is_parallel": true, "self": 30.372874912755833, "children": { "UnityEnvironment._generate_step_input": { "total": 21.270293496020713, "count": 58897, "is_parallel": true, "self": 21.270293496020713 }, "communicator.exchange": { "total": 1300.3045197430047, "count": 58897, "is_parallel": true, "self": 1300.3045197430047 }, "steps_from_proto": { "total": 97.95034368107918, "count": 58897, "is_parallel": true, "self": 20.66544297605651, "children": { "_process_rank_one_or_two_observation": { "total": 77.28490070502266, "count": 471176, "is_parallel": true, "self": 77.28490070502266 } } } } } } } } } } }, "trainer_advance": { "total": 583.0308039521706, "count": 58898, "self": 2.6356087911763098, "children": { "process_trajectory": { "total": 117.40548396100075, "count": 58898, "self": 117.21255378300066, "children": { "RLTrainer._checkpoint": { "total": 0.19293017800009693, "count": 2, "self": 0.19293017800009693 } } }, "_update_policy": { "total": 462.9897111999935, "count": 426, "self": 257.0169891231153, "children": { "TorchPPOOptimizer.update": { "total": 205.9727220768782, "count": 20493, "self": 205.9727220768782 } } } } } } }, "trainer_threads": { "total": 1.168999915535096e-06, "count": 1, "self": 1.168999915535096e-06 }, "TrainerController._save_models": { "total": 0.07930499500071164, "count": 1, "self": 0.001485969000896148, "children": { "RLTrainer._checkpoint": { "total": 0.0778190259998155, "count": 1, "self": 0.0778190259998155 } } } } } } }