{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.18840862810611725, "min": 0.18400797247886658, "max": 0.2804012894630432, "count": 34 }, "Pyramids.Policy.Entropy.sum": { "value": 5625.1279296875, "min": 3084.85693359375, "max": 8434.470703125, "count": 34 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 222.52592592592592, "min": 192.1627906976744, "max": 310.87368421052633, "count": 34 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30041.0, "min": 8263.0, "max": 31917.0, "count": 34 }, "Pyramids.Step.mean": { "value": 2999912.0, "min": 2009986.0, "max": 2999912.0, "count": 34 }, "Pyramids.Step.sum": { "value": 2999912.0, "min": 2009986.0, "max": 2999912.0, "count": 34 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.8403334021568298, "min": 0.6287362575531006, "max": 0.8403334021568298, "count": 34 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 258.82269287109375, "min": 74.38394165039062, "max": 258.82269287109375, "count": 34 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.008804552257061005, "min": -0.014464023523032665, "max": 0.02289220131933689, "count": 34 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 2.7118020057678223, "min": -1.8769246339797974, "max": 6.798983573913574, "count": 34 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.777474061537672, "min": 1.6048926098566307, "max": 1.8078372076500293, "count": 34 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 239.95899830758572, "min": 77.73699992895126, "max": 239.95899830758572, "count": 34 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.777474061537672, "min": 1.6048926098566307, "max": 1.8078372076500293, "count": 34 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 239.95899830758572, "min": 77.73699992895126, "max": 239.95899830758572, "count": 34 }, "Pyramids.Policy.RndReward.mean": { "value": 0.010327311727289472, "min": 0.010327311727289472, "max": 0.016723708555984654, "count": 34 }, "Pyramids.Policy.RndReward.sum": { "value": 1.3941870831840788, "min": 0.4957260352821322, "max": 1.8668560988735408, "count": 34 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.0678519000062368, "min": 0.06323107099021961, "max": 0.07358351286910916, "count": 34 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9499266000873152, "min": 0.2692302552476416, "max": 1.0497650696100511, "count": 34 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.015059468376675897, "min": 0.011901597794868784, "max": 0.016053768207105655, "count": 34 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.21083255727346256, "min": 0.06421507282842262, "max": 0.22995169926434758, "count": 34 }, "Pyramids.Policy.LearningRate.mean": { "value": 1.5854923286785776e-06, "min": 1.5854923286785776e-06, "max": 9.947019184329167e-05, "count": 34 }, "Pyramids.Policy.LearningRate.sum": { "value": 2.2196892601500087e-05, "min": 2.2196892601500087e-05, "max": 0.0014623016125664666, "count": 34 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10052846428571428, "min": 0.10052846428571428, "max": 0.13315670833333335, "count": 34 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4073985, "min": 0.5326268333333334, "max": 1.9874335333333333, "count": 34 }, "Pyramids.Policy.Beta.mean": { "value": 6.279358214285736e-05, "min": 6.279358214285736e-05, "max": 0.003322355162500001, "count": 34 }, "Pyramids.Policy.Beta.sum": { "value": 0.0008791101500000031, "min": 0.0008791101500000031, "max": 0.04884460998, "count": 34 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.00449164304882288, "min": 0.0044595287181437016, "max": 0.005885581020265818, "count": 34 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.06288300454616547, "min": 0.02354232408106327, "max": 0.08803229033946991, "count": 34 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 34 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 34 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1753093556", "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": "2.7.1+cu126", "numpy_version": "1.23.5", "end_time_seconds": "1753096027" }, "total": 2471.187962529001, "count": 1, "self": 0.47706635700069455, "children": { "run_training.setup": { "total": 0.02064571499977319, "count": 1, "self": 0.02064571499977319 }, "TrainerController.start_learning": { "total": 2470.6902504570007, "count": 1, "self": 1.2502839620237864, "children": { "TrainerController._reset_env": { "total": 2.2784153870006776, "count": 1, "self": 2.2784153870006776 }, "TrainerController.advance": { "total": 2467.077936038975, "count": 65747, "self": 1.3252463601666022, "children": { "env_step": { "total": 1814.2487259380023, "count": 65747, "self": 1675.5348490689512, "children": { "SubprocessEnvManager._take_step": { "total": 137.9759848011763, "count": 65747, "self": 4.379366755234514, "children": { "TorchPolicy.evaluate": { "total": 133.5966180459418, "count": 62556, "self": 133.5966180459418 } } }, "workers": { "total": 0.7378920678747818, "count": 65747, "self": 0.0, "children": { "worker_root": { "total": 2465.483885176981, "count": 65747, "is_parallel": true, "self": 897.5958427070655, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0020146099996054545, "count": 1, "is_parallel": true, "self": 0.0006397510005626827, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013748589990427718, "count": 8, "is_parallel": true, "self": 0.0013748589990427718 } } }, "UnityEnvironment.step": { "total": 0.09754352199979621, "count": 1, "is_parallel": true, "self": 0.0005564289995163563, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004128700002183905, "count": 1, "is_parallel": true, "self": 0.0004128700002183905 }, "communicator.exchange": { "total": 0.09495889400022861, "count": 1, "is_parallel": true, "self": 0.09495889400022861 }, "steps_from_proto": { "total": 0.0016153289998328546, "count": 1, "is_parallel": true, "self": 0.00035787800061370945, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012574509992191452, "count": 8, "is_parallel": true, "self": 0.0012574509992191452 } } } } } } }, "UnityEnvironment.step": { "total": 1567.8880424699155, "count": 65746, "is_parallel": true, "self": 31.039047085002494, "children": { "UnityEnvironment._generate_step_input": { "total": 21.627355150889343, "count": 65746, "is_parallel": true, "self": 21.627355150889343 }, "communicator.exchange": { "total": 1423.794196472004, "count": 65746, "is_parallel": true, "self": 1423.794196472004 }, "steps_from_proto": { "total": 91.42744376201972, "count": 65746, "is_parallel": true, "self": 17.88784387161013, "children": { "_process_rank_one_or_two_observation": { "total": 73.53959989040959, "count": 525968, "is_parallel": true, "self": 73.53959989040959 } } } } } } } } } } }, "trainer_advance": { "total": 651.5039637408063, "count": 65747, "self": 2.4893087617301717, "children": { "process_trajectory": { "total": 127.4065734170872, "count": 65747, "self": 127.15094464108734, "children": { "RLTrainer._checkpoint": { "total": 0.2556287759998668, "count": 2, "self": 0.2556287759998668 } } }, "_update_policy": { "total": 521.6080815619889, "count": 473, "self": 288.9219459850201, "children": { "TorchPPOOptimizer.update": { "total": 232.6861355769688, "count": 22761, "self": 232.6861355769688 } } } } } } }, "trainer_threads": { "total": 8.750012057134882e-07, "count": 1, "self": 8.750012057134882e-07 }, "TrainerController._save_models": { "total": 0.08361419399989245, "count": 1, "self": 0.0016051209986471804, "children": { "RLTrainer._checkpoint": { "total": 0.08200907300124527, "count": 1, "self": 0.08200907300124527 } } } } } } }