{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.18350118398666382, "min": 0.18278071284294128, "max": 1.3706443309783936, "count": 50 }, "Pyramids.Policy.Entropy.sum": { "value": 5502.099609375, "min": 5460.025390625, "max": 41579.8671875, "count": 50 }, "Pyramids.Step.mean": { "value": 1499901.0, "min": 29952.0, "max": 1499901.0, "count": 50 }, "Pyramids.Step.sum": { "value": 1499901.0, "min": 29952.0, "max": 1499901.0, "count": 50 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.7083656787872314, "min": -0.049884118139743805, "max": 0.7608505487442017, "count": 50 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 201.88421630859375, "min": -12.022072792053223, "max": 223.6900634765625, "count": 50 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.006795857101678848, "min": -0.004466857761144638, "max": 0.45243701338768005, "count": 50 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 1.936819314956665, "min": -1.2551870346069336, "max": 107.22756958007812, "count": 50 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07382442496298924, "min": 0.06461313227815221, "max": 0.07393613607690838, "count": 50 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.0335419494818494, "min": 0.5018676308145273, "max": 1.082827937391509, "count": 50 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.015811939797038408, "min": 0.00020058981358704928, "max": 0.017626756042729886, "count": 50 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2213671571585377, "min": 0.001404128695109345, "max": 0.2567393596043842, "count": 50 }, "Pyramids.Policy.LearningRate.mean": { "value": 3.1430846666238102e-06, "min": 3.1430846666238102e-06, "max": 0.00029676708679192377, "count": 50 }, "Pyramids.Policy.LearningRate.sum": { "value": 4.4003185332733344e-05, "min": 4.4003185332733344e-05, "max": 0.0038249406250198664, "count": 50 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10104766190476193, "min": 0.10104766190476193, "max": 0.19892236190476195, "count": 50 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.414667266666667, "min": 1.3794090666666667, "max": 2.7749801333333335, "count": 50 }, "Pyramids.Policy.Beta.mean": { "value": 0.00011466142428571429, "min": 0.00011466142428571429, "max": 0.009892343954285714, "count": 50 }, "Pyramids.Policy.Beta.sum": { "value": 0.00160525994, "min": 0.00160525994, "max": 0.12752051532000003, "count": 50 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.008289541117846966, "min": 0.008289541117846966, "max": 0.5864227414131165, "count": 50 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.11605358123779297, "min": 0.11605358123779297, "max": 4.104959011077881, "count": 50 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 285.7943925233645, "min": 241.6829268292683, "max": 999.0, "count": 50 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30580.0, "min": 15984.0, "max": 33285.0, "count": 50 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6394205472179662, "min": -1.0000000521540642, "max": 1.7444187964384372, "count": 50 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 175.4179985523224, "min": -32.000001668930054, "max": 212.27179804444313, "count": 50 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6394205472179662, "min": -1.0000000521540642, "max": 1.7444187964384372, "count": 50 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 175.4179985523224, "min": -32.000001668930054, "max": 212.27179804444313, "count": 50 }, "Pyramids.Policy.RndReward.mean": { "value": 0.025221727137352126, "min": 0.022200211014918512, "max": 12.058133356273174, "count": 50 }, "Pyramids.Policy.RndReward.sum": { "value": 2.6987248036966776, "min": 2.5448229197063483, "max": 192.9301337003708, "count": 50 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 50 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 50 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1680708260", "python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \n[GCC 9.4.0]", "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", "mlagents_version": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.11.0+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1680712117" }, "total": 3857.337979299, "count": 1, "self": 0.4802387469990208, "children": { "run_training.setup": { "total": 0.12208969899984368, "count": 1, "self": 0.12208969899984368 }, "TrainerController.start_learning": { "total": 3856.735650853001, "count": 1, "self": 2.5176135073270416, "children": { "TrainerController._reset_env": { "total": 4.187815661998684, "count": 1, "self": 4.187815661998684 }, "TrainerController.advance": { "total": 3849.895607516677, "count": 96901, "self": 2.5142060716370906, "children": { "env_step": { "total": 2840.20973961213, "count": 96901, "self": 2653.65257890089, "children": { "SubprocessEnvManager._take_step": { "total": 185.08426722985132, "count": 96901, "self": 7.56914735270766, "children": { "TorchPolicy.evaluate": { "total": 177.51511987714366, "count": 93805, "self": 177.51511987714366 } } }, "workers": { "total": 1.4728934813883825, "count": 96901, "self": 0.0, "children": { "worker_root": { "total": 3847.686080408068, "count": 96901, "is_parallel": true, "self": 1380.8562785770027, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0019676479987538187, "count": 1, "is_parallel": true, "self": 0.0006497310005215695, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013179169982322492, "count": 8, "is_parallel": true, "self": 0.0013179169982322492 } } }, "UnityEnvironment.step": { "total": 0.051746670998909394, "count": 1, "is_parallel": true, "self": 0.0006192049968376523, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005490420007845387, "count": 1, "is_parallel": true, "self": 0.0005490420007845387 }, "communicator.exchange": { "total": 0.048714160000599804, "count": 1, "is_parallel": true, "self": 0.048714160000599804 }, "steps_from_proto": { "total": 0.001864264000687399, "count": 1, "is_parallel": true, "self": 0.0004189040046185255, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014453599960688734, "count": 8, "is_parallel": true, "self": 0.0014453599960688734 } } } } } } }, "UnityEnvironment.step": { "total": 2466.829801831065, "count": 96900, "is_parallel": true, "self": 52.83836421567321, "children": { "UnityEnvironment._generate_step_input": { "total": 36.516817352701764, "count": 96900, "is_parallel": true, "self": 36.516817352701764 }, "communicator.exchange": { "total": 2224.4332258787636, "count": 96900, "is_parallel": true, "self": 2224.4332258787636 }, "steps_from_proto": { "total": 153.04139438392667, "count": 96900, "is_parallel": true, "self": 33.25704529172435, "children": { "_process_rank_one_or_two_observation": { "total": 119.78434909220232, "count": 775200, "is_parallel": true, "self": 119.78434909220232 } } } } } } } } } } }, "trainer_advance": { "total": 1007.1716618329101, "count": 96901, "self": 4.574954038829674, "children": { "process_trajectory": { "total": 172.5113150200832, "count": 96901, "self": 171.96421503308375, "children": { "RLTrainer._checkpoint": { "total": 0.5470999869994557, "count": 3, "self": 0.5470999869994557 } } }, "_update_policy": { "total": 830.0853927739972, "count": 688, "self": 510.09852103289813, "children": { "TorchPPOOptimizer.update": { "total": 319.9868717410991, "count": 34185, "self": 319.9868717410991 } } } } } } }, "trainer_threads": { "total": 1.1209995136596262e-06, "count": 1, "self": 1.1209995136596262e-06 }, "TrainerController._save_models": { "total": 0.13461304599877622, "count": 1, "self": 0.002820503999828361, "children": { "RLTrainer._checkpoint": { "total": 0.13179254199894785, "count": 1, "self": 0.13179254199894785 } } } } } } }