{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.20152749121189117, "min": 0.19390833377838135, "max": 1.4351239204406738, "count": 100 }, "Pyramids.Policy.Entropy.sum": { "value": 6026.47802734375, "min": 5786.224609375, "max": 43535.91796875, "count": 100 }, "Pyramids.Step.mean": { "value": 2999891.0, "min": 29944.0, "max": 2999891.0, "count": 100 }, "Pyramids.Step.sum": { "value": 2999891.0, "min": 29944.0, "max": 2999891.0, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.6537366509437561, "min": -0.08583556115627289, "max": 0.718716025352478, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 184.35372924804688, "min": -20.686370849609375, "max": 207.70892333984375, "count": 100 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.0031279141549021006, "min": -0.021385660395026207, "max": 0.3585151433944702, "count": 100 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 0.8820717930793762, "min": -5.752742767333984, "max": 84.96808624267578, "count": 100 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06887535228509246, "min": 0.06403904496013033, "max": 0.07478861652219036, "count": 100 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9642549319912944, "min": 0.4934077897348612, "max": 1.0825659808275911, "count": 100 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.015871344020608774, "min": 0.000385244314551386, "max": 0.01638932239300283, "count": 100 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.22219881628852284, "min": 0.005008176089168018, "max": 0.24325015664319782, "count": 100 }, "Pyramids.Policy.LearningRate.mean": { "value": 1.4721995093000029e-06, "min": 1.4721995093000029e-06, "max": 0.0002984110862439238, "count": 100 }, "Pyramids.Policy.LearningRate.sum": { "value": 2.061079313020004e-05, "min": 2.061079313020004e-05, "max": 0.003802569432476933, "count": 100 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10049070000000002, "min": 0.10049070000000002, "max": 0.19947036190476192, "count": 100 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4068698000000002, "min": 1.3962925333333334, "max": 2.7675230666666666, "count": 100 }, "Pyramids.Policy.Beta.mean": { "value": 5.902093000000011e-05, "min": 5.902093000000011e-05, "max": 0.009947089154285714, "count": 100 }, "Pyramids.Policy.Beta.sum": { "value": 0.0008262930200000016, "min": 0.0008262930200000016, "max": 0.12677555436000001, "count": 100 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.003972571808844805, "min": 0.003952003084123135, "max": 0.4274613559246063, "count": 100 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.05561600625514984, "min": 0.055328045040369034, "max": 2.992229461669922, "count": 100 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 264.76576576576576, "min": 264.76576576576576, "max": 999.0, "count": 100 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29389.0, "min": 16743.0, "max": 33023.0, "count": 100 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.716991048638842, "min": -0.9999750521965325, "max": 1.7293333175281684, "count": 100 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 192.3029974475503, "min": -31.99920167028904, "max": 192.3029974475503, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.716991048638842, "min": -0.9999750521965325, "max": 1.7293333175281684, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 192.3029974475503, "min": -31.99920167028904, "max": 192.3029974475503, "count": 100 }, "Pyramids.Policy.RndReward.mean": { "value": 0.011150953349767536, "min": 0.0111108166596523, "max": 7.523499069844975, "count": 100 }, "Pyramids.Policy.RndReward.sum": { "value": 1.248906775173964, "min": 1.1555249326038393, "max": 127.89948418736458, "count": 100 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 100 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 100 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1710953592", "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", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.2.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1710964563" }, "total": 10970.622265953, "count": 1, "self": 0.8967133680016559, "children": { "run_training.setup": { "total": 0.08154976599962538, "count": 1, "self": 0.08154976599962538 }, "TrainerController.start_learning": { "total": 10969.644002818999, "count": 1, "self": 8.551903805770053, "children": { "TrainerController._reset_env": { "total": 4.388208878000114, "count": 1, "self": 4.388208878000114 }, "TrainerController.advance": { "total": 10956.542747404228, "count": 192592, "self": 9.244943533687547, "children": { "env_step": { "total": 7449.810262778045, "count": 192592, "self": 6886.727629546977, "children": { "SubprocessEnvManager._take_step": { "total": 557.593352741178, "count": 192592, "self": 23.5979281981472, "children": { "TorchPolicy.evaluate": { "total": 533.9954245430308, "count": 187553, "self": 533.9954245430308 } } }, "workers": { "total": 5.489280489890007, "count": 192592, "self": 0.0, "children": { "worker_root": { "total": 10947.93878881325, "count": 192592, "is_parallel": true, "self": 4718.062161258383, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.00810300000011921, "count": 1, "is_parallel": true, "self": 0.005532440996830701, "children": { "_process_rank_one_or_two_observation": { "total": 0.0025705590032885084, "count": 8, "is_parallel": true, "self": 0.0025705590032885084 } } }, "UnityEnvironment.step": { "total": 0.07006233100037207, "count": 1, "is_parallel": true, "self": 0.0008817750003800029, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00045843299994885456, "count": 1, "is_parallel": true, "self": 0.00045843299994885456 }, "communicator.exchange": { "total": 0.06647319100011373, "count": 1, "is_parallel": true, "self": 0.06647319100011373 }, "steps_from_proto": { "total": 0.002248931999929482, "count": 1, "is_parallel": true, "self": 0.00048600599984638393, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017629260000830982, "count": 8, "is_parallel": true, "self": 0.0017629260000830982 } } } } } } }, "UnityEnvironment.step": { "total": 6229.876627554867, "count": 192591, "is_parallel": true, "self": 175.5049392978617, "children": { "UnityEnvironment._generate_step_input": { "total": 94.90448410991121, "count": 192591, "is_parallel": true, "self": 94.90448410991121 }, "communicator.exchange": { "total": 5526.220749628055, "count": 192591, "is_parallel": true, "self": 5526.220749628055 }, "steps_from_proto": { "total": 433.2464545190387, "count": 192591, "is_parallel": true, "self": 96.92679814994153, "children": { "_process_rank_one_or_two_observation": { "total": 336.3196563690972, "count": 1540728, "is_parallel": true, "self": 336.3196563690972 } } } } } } } } } } }, "trainer_advance": { "total": 3497.487541092495, "count": 192592, "self": 19.219623630383467, "children": { "process_trajectory": { "total": 573.8579918151318, "count": 192592, "self": 573.1366333901306, "children": { "RLTrainer._checkpoint": { "total": 0.7213584250011991, "count": 6, "self": 0.7213584250011991 } } }, "_update_policy": { "total": 2904.40992564698, "count": 1396, "self": 1171.405735750739, "children": { "TorchPPOOptimizer.update": { "total": 1733.0041898962409, "count": 68271, "self": 1733.0041898962409 } } } } } } }, "trainer_threads": { "total": 1.6480007616337389e-06, "count": 1, "self": 1.6480007616337389e-06 }, "TrainerController._save_models": { "total": 0.1611410830009845, "count": 1, "self": 0.0037679520009987755, "children": { "RLTrainer._checkpoint": { "total": 0.15737313099998573, "count": 1, "self": 0.15737313099998573 } } } } } } }