{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.45749416947364807, "min": 0.45749416947364807, "max": 1.4558703899383545, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 13629.666015625, "min": 13629.666015625, "max": 44165.28515625, "count": 33 }, "Pyramids.Step.mean": { "value": 989933.0, "min": 29952.0, "max": 989933.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989933.0, "min": 29952.0, "max": 989933.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.6087445020675659, "min": -0.0848848819732666, "max": 0.6788182854652405, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 171.0572052001953, "min": -20.54214096069336, "max": 194.14202880859375, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.008265988901257515, "min": -0.04506039619445801, "max": 0.320005863904953, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 2.3227429389953613, "min": -11.805824279785156, "max": 77.12141418457031, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06922707926250654, "min": 0.06540764389065269, "max": 0.07484400565930023, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.0384061889375982, "min": 0.5114073389711262, "max": 1.1226600848895034, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.016812850951861583, "min": 0.0013469616726810869, "max": 0.018410098856563063, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.25219276427792375, "min": 0.016163540072173042, "max": 0.27615148284844593, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.5116174961600004e-06, "min": 7.5116174961600004e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0001126742624424, "min": 0.0001126742624424, "max": 0.003633725888758099, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10250383999999998, "min": 0.10250383999999998, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5375575999999997, "min": 1.3886848, "max": 2.6112419000000004, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026013361600000004, "min": 0.00026013361600000004, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003902004240000001, "min": 0.003902004240000001, "max": 0.12114306581, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.009413931518793106, "min": 0.009344969876110554, "max": 0.5517582297325134, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.1412089765071869, "min": 0.1308295726776123, "max": 3.8623077869415283, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 316.7395833333333, "min": 277.1747572815534, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30407.0, "min": 15984.0, "max": 33081.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.5999020639186103, "min": -1.0000000521540642, "max": 1.7246538314681787, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 153.5905981361866, "min": -29.752601645886898, "max": 183.13219835609198, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.5999020639186103, "min": -1.0000000521540642, "max": 1.7246538314681787, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 153.5905981361866, "min": -29.752601645886898, "max": 183.13219835609198, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.03102739682359849, "min": 0.02734783593866898, "max": 11.630704985931516, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.978630095065455, "min": 2.844174937621574, "max": 186.09127977490425, "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": "1684517027", "python_version": "3.10.11 (main, Apr 5 2023, 14:15:10) [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": "1684519254" }, "total": 2226.9366803289995, "count": 1, "self": 0.4741458559997227, "children": { "run_training.setup": { "total": 0.05746653000005608, "count": 1, "self": 0.05746653000005608 }, "TrainerController.start_learning": { "total": 2226.4050679429997, "count": 1, "self": 1.3660064850187155, "children": { "TrainerController._reset_env": { "total": 4.809953503000088, "count": 1, "self": 4.809953503000088 }, "TrainerController.advance": { "total": 2220.137533199982, "count": 64130, "self": 1.4112380209380717, "children": { "env_step": { "total": 1586.6378129690293, "count": 64130, "self": 1478.9245043249875, "children": { "SubprocessEnvManager._take_step": { "total": 106.93419555203127, "count": 64130, "self": 4.689354074014318, "children": { "TorchPolicy.evaluate": { "total": 102.24484147801695, "count": 62552, "self": 102.24484147801695 } } }, "workers": { "total": 0.7791130920104479, "count": 64130, "self": 0.0, "children": { "worker_root": { "total": 2221.371324562086, "count": 64130, "is_parallel": true, "self": 853.3820651779797, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002522336000311043, "count": 1, "is_parallel": true, "self": 0.0006992149997131492, "children": { "_process_rank_one_or_two_observation": { "total": 0.0018231210005978937, "count": 8, "is_parallel": true, "self": 0.0018231210005978937 } } }, "UnityEnvironment.step": { "total": 0.046621911999864096, "count": 1, "is_parallel": true, "self": 0.0005524769999283308, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005449919999591657, "count": 1, "is_parallel": true, "self": 0.0005449919999591657 }, "communicator.exchange": { "total": 0.04380928299997322, "count": 1, "is_parallel": true, "self": 0.04380928299997322 }, "steps_from_proto": { "total": 0.0017151600000033795, "count": 1, "is_parallel": true, "self": 0.00033765000034691184, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013775099996564677, "count": 8, "is_parallel": true, "self": 0.0013775099996564677 } } } } } } }, "UnityEnvironment.step": { "total": 1367.9892593841064, "count": 64129, "is_parallel": true, "self": 30.988338629293594, "children": { "UnityEnvironment._generate_step_input": { "total": 22.62026800297417, "count": 64129, "is_parallel": true, "self": 22.62026800297417 }, "communicator.exchange": { "total": 1218.7628609198773, "count": 64129, "is_parallel": true, "self": 1218.7628609198773 }, "steps_from_proto": { "total": 95.61779183196131, "count": 64129, "is_parallel": true, "self": 19.24577835194532, "children": { "_process_rank_one_or_two_observation": { "total": 76.372013480016, "count": 513032, "is_parallel": true, "self": 76.372013480016 } } } } } } } } } } }, "trainer_advance": { "total": 632.0884822100147, "count": 64130, "self": 2.5484046180808946, "children": { "process_trajectory": { "total": 106.98952641893493, "count": 64130, "self": 106.79240493093539, "children": { "RLTrainer._checkpoint": { "total": 0.19712148799953866, "count": 2, "self": 0.19712148799953866 } } }, "_update_policy": { "total": 522.5505511729989, "count": 455, "self": 335.42317178798567, "children": { "TorchPPOOptimizer.update": { "total": 187.12737938501323, "count": 22767, "self": 187.12737938501323 } } } } } } }, "trainer_threads": { "total": 9.859995770966634e-07, "count": 1, "self": 9.859995770966634e-07 }, "TrainerController._save_models": { "total": 0.09157376899929659, "count": 1, "self": 0.0013438109990602243, "children": { "RLTrainer._checkpoint": { "total": 0.09022995800023637, "count": 1, "self": 0.09022995800023637 } } } } } } }