{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.3748374879360199, "min": 0.3748374879360199, "max": 0.5130709409713745, "count": 17 }, "Pyramids.Policy.Entropy.sum": { "value": 11191.1484375, "min": 10753.966796875, "max": 15011.27734375, "count": 17 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 253.2136752136752, "min": 253.2136752136752, "max": 367.75581395348837, "count": 17 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29626.0, "min": 15649.0, "max": 31913.0, "count": 17 }, "Pyramids.Step.mean": { "value": 1499946.0, "min": 1019944.0, "max": 1499946.0, "count": 17 }, "Pyramids.Step.sum": { "value": 1499946.0, "min": 1019944.0, "max": 1499946.0, "count": 17 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.7240810990333557, "min": 0.5280531644821167, "max": 0.7240810990333557, "count": 17 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 212.15576171875, "min": 98.05105590820312, "max": 212.15576171875, "count": 17 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.015062732622027397, "min": -0.038299426436424255, "max": 0.024049047380685806, "count": 17 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -4.4133806228637695, "min": -10.953636169433594, "max": 6.661586284637451, "count": 17 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.7446271010627181, "min": 1.5564873341856331, "max": 1.7446271010627181, "count": 17 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 205.86599792540073, "min": 76.35099945962429, "max": 205.86599792540073, "count": 17 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.7446271010627181, "min": 1.5564873341856331, "max": 1.7446271010627181, "count": 17 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 205.86599792540073, "min": 76.35099945962429, "max": 205.86599792540073, "count": 17 }, "Pyramids.Policy.RndReward.mean": { "value": 0.02108566748581124, "min": 0.02108566748581124, "max": 0.036422244585039495, "count": 17 }, "Pyramids.Policy.RndReward.sum": { "value": 2.4881087633257266, "min": 1.5972690338967368, "max": 3.059468545143318, "count": 17 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06781738295600716, "min": 0.06358014467003245, "max": 0.0706216018879786, "count": 17 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9494433613841001, "min": 0.6303121379799753, "max": 1.0525073112221435, "count": 17 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.015996850570073582, "min": 0.012975057341261871, "max": 0.015996850570073582, "count": 17 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.22395590798103016, "min": 0.11677551607135683, "max": 0.23405582210398276, "count": 17 }, "Pyramids.Policy.LearningRate.mean": { "value": 3.0954703967809542e-06, "min": 3.0954703967809542e-06, "max": 9.788917848140741e-05, "count": 17 }, "Pyramids.Policy.LearningRate.sum": { "value": 4.333658555493336e-05, "min": 4.333658555493336e-05, "max": 0.0013029187656940667, "count": 17 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10103179047619049, "min": 0.10103179047619049, "max": 0.13262970370370375, "count": 17 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4144450666666668, "min": 1.1936673333333336, "max": 1.9053473333333335, "count": 17 }, "Pyramids.Policy.Beta.mean": { "value": 0.00011307586857142865, "min": 0.00011307586857142865, "max": 0.0032697074000000003, "count": 17 }, "Pyramids.Policy.Beta.sum": { "value": 0.001583062160000001, "min": 0.001583062160000001, "max": 0.04352716274000001, "count": 17 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.007952400483191013, "min": 0.007952400483191013, "max": 0.009898611344397068, "count": 17 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.11133360862731934, "min": 0.08908750116825104, "max": 0.13826604187488556, "count": 17 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 17 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 17 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1717186256", "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 --resume", "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": "1717187516" }, "total": 1259.4383329230004, "count": 1, "self": 0.4760205799993855, "children": { "run_training.setup": { "total": 0.05126818100052333, "count": 1, "self": 0.05126818100052333 }, "TrainerController.start_learning": { "total": 1258.9110441620005, "count": 1, "self": 0.7677809090109804, "children": { "TrainerController._reset_env": { "total": 2.232809957000427, "count": 1, "self": 2.232809957000427 }, "TrainerController.advance": { "total": 1255.822123611989, "count": 32541, "self": 0.8053479979917029, "children": { "env_step": { "total": 931.4630197449387, "count": 32541, "self": 860.8604555749016, "children": { "SubprocessEnvManager._take_step": { "total": 70.13547415700396, "count": 32541, "self": 2.5215686200272103, "children": { "TorchPolicy.evaluate": { "total": 67.61390553697674, "count": 31295, "self": 67.61390553697674 } } }, "workers": { "total": 0.46709001303315745, "count": 32541, "self": 0.0, "children": { "worker_root": { "total": 1256.027467099957, "count": 32541, "is_parallel": true, "self": 461.83187196688505, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0021142400000826456, "count": 1, "is_parallel": true, "self": 0.0006239159993128851, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014903240007697605, "count": 8, "is_parallel": true, "self": 0.0014903240007697605 } } }, "UnityEnvironment.step": { "total": 0.088227979000294, "count": 1, "is_parallel": true, "self": 0.0006633509992752806, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005221680003160145, "count": 1, "is_parallel": true, "self": 0.0005221680003160145 }, "communicator.exchange": { "total": 0.08452152000063506, "count": 1, "is_parallel": true, "self": 0.08452152000063506 }, "steps_from_proto": { "total": 0.0025209400000676396, "count": 1, "is_parallel": true, "self": 0.0004011549999631825, "children": { "_process_rank_one_or_two_observation": { "total": 0.002119785000104457, "count": 8, "is_parallel": true, "self": 0.002119785000104457 } } } } } } }, "UnityEnvironment.step": { "total": 794.195595133072, "count": 32540, "is_parallel": true, "self": 17.651247055092426, "children": { "UnityEnvironment._generate_step_input": { "total": 12.197150454011535, "count": 32540, "is_parallel": true, "self": 12.197150454011535 }, "communicator.exchange": { "total": 711.9384423460306, "count": 32540, "is_parallel": true, "self": 711.9384423460306 }, "steps_from_proto": { "total": 52.408755277937416, "count": 32540, "is_parallel": true, "self": 10.992631100058134, "children": { "_process_rank_one_or_two_observation": { "total": 41.41612417787928, "count": 260320, "is_parallel": true, "self": 41.41612417787928 } } } } } } } } } } }, "trainer_advance": { "total": 323.5537558690585, "count": 32541, "self": 1.5293286400828947, "children": { "process_trajectory": { "total": 69.16295337697557, "count": 32541, "self": 69.05397919097504, "children": { "RLTrainer._checkpoint": { "total": 0.10897418600052333, "count": 1, "self": 0.10897418600052333 } } }, "_update_policy": { "total": 252.86147385200002, "count": 236, "self": 149.54518986398216, "children": { "TorchPPOOptimizer.update": { "total": 103.31628398801786, "count": 11364, "self": 103.31628398801786 } } } } } } }, "trainer_threads": { "total": 1.002999852062203e-06, "count": 1, "self": 1.002999852062203e-06 }, "TrainerController._save_models": { "total": 0.0883286810003483, "count": 1, "self": 0.0020003220006401534, "children": { "RLTrainer._checkpoint": { "total": 0.08632835899970814, "count": 1, "self": 0.08632835899970814 } } } } } } }