{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.38989493250846863, "min": 0.38989493250846863, "max": 1.459467887878418, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 11821.6142578125, "min": 11744.8359375, "max": 44274.41796875, "count": 33 }, "Pyramids.Step.mean": { "value": 989886.0, "min": 29952.0, "max": 989886.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989886.0, "min": 29952.0, "max": 989886.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.3971599042415619, "min": -0.13952460885047913, "max": 0.3971599042415619, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 105.64453125, "min": -33.06733322143555, "max": 105.64453125, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.05755922943353653, "min": -0.003959978930652142, "max": 0.23779860138893127, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 15.310754776000977, "min": -1.0375144481658936, "max": 56.35826873779297, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06767690789032108, "min": 0.06467115107404332, "max": 0.07372450696796481, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9474767104644951, "min": 0.5160715487757537, "max": 1.0568009033837977, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.013338869866163892, "min": 0.00016369380130408785, "max": 0.015343458799179643, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.18674417812629449, "min": 0.0018006318143449663, "max": 0.214808423188515, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.358626118585714e-06, "min": 7.358626118585714e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0001030207656602, "min": 0.0001030207656602, "max": 0.003117604660798499, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10245284285714285, "min": 0.10245284285714285, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4343397999999998, "min": 1.3886848, "max": 2.4018118999999998, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002550390014285715, "min": 0.0002550390014285715, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0035705460200000008, "min": 0.0035705460200000008, "max": 0.10393622984999999, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.012142250314354897, "min": 0.011802700348198414, "max": 0.39324983954429626, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.16999150812625885, "min": 0.16999150812625885, "max": 2.752748966217041, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 434.5970149253731, "min": 434.5970149253731, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29118.0, "min": 15984.0, "max": 33029.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.4459492341795963, "min": -1.0000000521540642, "max": 1.4459492341795963, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 96.87859869003296, "min": -31.998001664876938, "max": 100.19379919022322, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.4459492341795963, "min": -1.0000000521540642, "max": 1.4459492341795963, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 96.87859869003296, "min": -31.998001664876938, "max": 100.19379919022322, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.05406994959162487, "min": 0.05406994959162487, "max": 7.976564284414053, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.6226866226388665, "min": 3.607405538466992, "max": 127.62502855062485, "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": "1746254014", "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": "2.7.0+cu126", "numpy_version": "1.23.5", "end_time_seconds": "1746255738" }, "total": 1724.25962813, "count": 1, "self": 0.37215418400001, "children": { "run_training.setup": { "total": 0.020224910000024465, "count": 1, "self": 0.020224910000024465 }, "TrainerController.start_learning": { "total": 1723.867249036, "count": 1, "self": 1.5361950000292381, "children": { "TrainerController._reset_env": { "total": 2.3355003340000167, "count": 1, "self": 2.3355003340000167 }, "TrainerController.advance": { "total": 1719.9123633599713, "count": 63432, "self": 1.4718718699273268, "children": { "env_step": { "total": 1077.400158871074, "count": 63432, "self": 922.9277329039546, "children": { "SubprocessEnvManager._take_step": { "total": 153.5843421890877, "count": 63432, "self": 4.532435215021906, "children": { "TorchPolicy.evaluate": { "total": 149.0519069740658, "count": 62551, "self": 149.0519069740658 } } }, "workers": { "total": 0.8880837780316142, "count": 63432, "self": 0.0, "children": { "worker_root": { "total": 1721.5458141550184, "count": 63432, "is_parallel": true, "self": 894.7023304289614, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.001964313999906153, "count": 1, "is_parallel": true, "self": 0.0006639169996560668, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013003970002500864, "count": 8, "is_parallel": true, "self": 0.0013003970002500864 } } }, "UnityEnvironment.step": { "total": 0.04024367700003495, "count": 1, "is_parallel": true, "self": 0.00035679600023286184, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003021649999936926, "count": 1, "is_parallel": true, "self": 0.0003021649999936926 }, "communicator.exchange": { "total": 0.03846786899998733, "count": 1, "is_parallel": true, "self": 0.03846786899998733 }, "steps_from_proto": { "total": 0.001116846999821064, "count": 1, "is_parallel": true, "self": 0.00024726099991312367, "children": { "_process_rank_one_or_two_observation": { "total": 0.0008695859999079403, "count": 8, "is_parallel": true, "self": 0.0008695859999079403 } } } } } } }, "UnityEnvironment.step": { "total": 826.843483726057, "count": 63431, "is_parallel": true, "self": 20.94113800708533, "children": { "UnityEnvironment._generate_step_input": { "total": 14.131560981994653, "count": 63431, "is_parallel": true, "self": 14.131560981994653 }, "communicator.exchange": { "total": 729.2698708250127, "count": 63431, "is_parallel": true, "self": 729.2698708250127 }, "steps_from_proto": { "total": 62.50091391196429, "count": 63431, "is_parallel": true, "self": 13.66639323884965, "children": { "_process_rank_one_or_two_observation": { "total": 48.83452067311464, "count": 507448, "is_parallel": true, "self": 48.83452067311464 } } } } } } } } } } }, "trainer_advance": { "total": 641.0403326189701, "count": 63432, "self": 2.740270974936493, "children": { "process_trajectory": { "total": 118.41188175502657, "count": 63432, "self": 118.21019919002674, "children": { "RLTrainer._checkpoint": { "total": 0.20168256499982817, "count": 2, "self": 0.20168256499982817 } } }, "_update_policy": { "total": 519.888179889007, "count": 439, "self": 285.700794121052, "children": { "TorchPPOOptimizer.update": { "total": 234.187385767955, "count": 22851, "self": 234.187385767955 } } } } } } }, "trainer_threads": { "total": 9.779996616998687e-07, "count": 1, "self": 9.779996616998687e-07 }, "TrainerController._save_models": { "total": 0.08318936399973609, "count": 1, "self": 0.00144750599974941, "children": { "RLTrainer._checkpoint": { "total": 0.08174185799998668, "count": 1, "self": 0.08174185799998668 } } } } } } }