| { |
| "name": "root", |
| "gauges": { |
| "Pyramids.Policy.Entropy.mean": { |
| "value": 0.2920001745223999, |
| "min": 0.2914068400859833, |
| "max": 1.521653652191162, |
| "count": 33 |
| }, |
| "Pyramids.Policy.Entropy.sum": { |
| "value": 8848.7734375, |
| "min": 8714.23046875, |
| "max": 46160.88671875, |
| "count": 33 |
| }, |
| "Pyramids.Step.mean": { |
| "value": 989982.0, |
| "min": 29952.0, |
| "max": 989982.0, |
| "count": 33 |
| }, |
| "Pyramids.Step.sum": { |
| "value": 989982.0, |
| "min": 29952.0, |
| "max": 989982.0, |
| "count": 33 |
| }, |
| "Pyramids.Policy.ExtrinsicValueEstimate.mean": { |
| "value": 0.4614899754524231, |
| "min": -0.2127297967672348, |
| "max": 0.5259947776794434, |
| "count": 33 |
| }, |
| "Pyramids.Policy.ExtrinsicValueEstimate.sum": { |
| "value": 123.67931365966797, |
| "min": -50.416961669921875, |
| "max": 144.6485595703125, |
| "count": 33 |
| }, |
| "Pyramids.Policy.RndValueEstimate.mean": { |
| "value": 0.019666768610477448, |
| "min": -0.004462243989109993, |
| "max": 0.1593952775001526, |
| "count": 33 |
| }, |
| "Pyramids.Policy.RndValueEstimate.sum": { |
| "value": 5.270693778991699, |
| "min": -1.1334099769592285, |
| "max": 38.41426086425781, |
| "count": 33 |
| }, |
| "Pyramids.Losses.PolicyLoss.mean": { |
| "value": 0.06864577795301255, |
| "min": 0.06392801569374405, |
| "max": 0.07604054467639586, |
| "count": 33 |
| }, |
| "Pyramids.Losses.PolicyLoss.sum": { |
| "value": 1.0296866692951883, |
| "min": 0.4855290729841539, |
| "max": 1.0740639513795605, |
| "count": 33 |
| }, |
| "Pyramids.Losses.ValueLoss.mean": { |
| "value": 0.011478397980034867, |
| "min": 0.001402071785139244, |
| "max": 0.016096375480083736, |
| "count": 33 |
| }, |
| "Pyramids.Losses.ValueLoss.sum": { |
| "value": 0.172175969700523, |
| "min": 0.013365910746686575, |
| "max": 0.2253492567211723, |
| "count": 33 |
| }, |
| "Pyramids.Policy.LearningRate.mean": { |
| "value": 7.470077510006671e-06, |
| "min": 7.470077510006671e-06, |
| "max": 0.00029515063018788575, |
| "count": 33 |
| }, |
| "Pyramids.Policy.LearningRate.sum": { |
| "value": 0.00011205116265010007, |
| "min": 0.00011205116265010007, |
| "max": 0.0033832472722510006, |
| "count": 33 |
| }, |
| "Pyramids.Policy.Epsilon.mean": { |
| "value": 0.10248999333333335, |
| "min": 0.10248999333333335, |
| "max": 0.19838354285714285, |
| "count": 33 |
| }, |
| "Pyramids.Policy.Epsilon.sum": { |
| "value": 1.5373499000000002, |
| "min": 1.3886848, |
| "max": 2.527749, |
| "count": 33 |
| }, |
| "Pyramids.Policy.Beta.mean": { |
| "value": 0.00025875033400000016, |
| "min": 0.00025875033400000016, |
| "max": 0.00983851593142857, |
| "count": 33 |
| }, |
| "Pyramids.Policy.Beta.sum": { |
| "value": 0.0038812550100000027, |
| "min": 0.0038812550100000027, |
| "max": 0.11280212510000001, |
| "count": 33 |
| }, |
| "Pyramids.Losses.RNDLoss.mean": { |
| "value": 0.007331249304115772, |
| "min": 0.007331249304115772, |
| "max": 0.21747584640979767, |
| "count": 33 |
| }, |
| "Pyramids.Losses.RNDLoss.sum": { |
| "value": 0.10996873676776886, |
| "min": 0.1039016991853714, |
| "max": 1.5223308801651, |
| "count": 33 |
| }, |
| "Pyramids.Environment.EpisodeLength.mean": { |
| "value": 400.50666666666666, |
| "min": 361.59090909090907, |
| "max": 999.0, |
| "count": 33 |
| }, |
| "Pyramids.Environment.EpisodeLength.sum": { |
| "value": 30038.0, |
| "min": 15984.0, |
| "max": 32829.0, |
| "count": 33 |
| }, |
| "Pyramids.Environment.CumulativeReward.mean": { |
| "value": 1.3861039790511132, |
| "min": -1.0000000521540642, |
| "max": 1.5204959763089816, |
| "count": 33 |
| }, |
| "Pyramids.Environment.CumulativeReward.sum": { |
| "value": 103.95779842883348, |
| "min": -30.65360175818205, |
| "max": 128.61819843947887, |
| "count": 33 |
| }, |
| "Pyramids.Policy.ExtrinsicReward.mean": { |
| "value": 1.3861039790511132, |
| "min": -1.0000000521540642, |
| "max": 1.5204959763089816, |
| "count": 33 |
| }, |
| "Pyramids.Policy.ExtrinsicReward.sum": { |
| "value": 103.95779842883348, |
| "min": -30.65360175818205, |
| "max": 128.61819843947887, |
| "count": 33 |
| }, |
| "Pyramids.Policy.RndReward.mean": { |
| "value": 0.030668593565545355, |
| "min": 0.029589406865852652, |
| "max": 4.517180601600558, |
| "count": 33 |
| }, |
| "Pyramids.Policy.RndReward.sum": { |
| "value": 2.3001445174159016, |
| "min": 2.094646116354852, |
| "max": 72.27488962560892, |
| "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": "1777407336", |
| "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": "2.8.0+cu128", |
| "numpy_version": "1.23.5", |
| "end_time_seconds": "1777409533" |
| }, |
| "total": 2197.699120857, |
| "count": 1, |
| "self": 0.7514971300006437, |
| "children": { |
| "run_training.setup": { |
| "total": 0.023171403999185713, |
| "count": 1, |
| "self": 0.023171403999185713 |
| }, |
| "TrainerController.start_learning": { |
| "total": 2196.924452323, |
| "count": 1, |
| "self": 1.3471051501146576, |
| "children": { |
| "TrainerController._reset_env": { |
| "total": 2.1205108799995287, |
| "count": 1, |
| "self": 2.1205108799995287 |
| }, |
| "TrainerController.advance": { |
| "total": 2193.349527696886, |
| "count": 63922, |
| "self": 1.3661196819448378, |
| "children": { |
| "env_step": { |
| "total": 1527.6667185170581, |
| "count": 63922, |
| "self": 1378.3921217711177, |
| "children": { |
| "SubprocessEnvManager._take_step": { |
| "total": 148.48744030504804, |
| "count": 63922, |
| "self": 4.542463373094506, |
| "children": { |
| "TorchPolicy.evaluate": { |
| "total": 143.94497693195353, |
| "count": 62551, |
| "self": 143.94497693195353 |
| } |
| } |
| }, |
| "workers": { |
| "total": 0.7871564408924314, |
| "count": 63922, |
| "self": 0.0, |
| "children": { |
| "worker_root": { |
| "total": 2190.3854201458225, |
| "count": 63922, |
| "is_parallel": true, |
| "self": 928.3390509038027, |
| "children": { |
| "run_training.setup": { |
| "total": 0.0, |
| "count": 0, |
| "is_parallel": true, |
| "self": 0.0, |
| "children": { |
| "steps_from_proto": { |
| "total": 0.003967310999541951, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.0012256789996172301, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 0.0027416319999247207, |
| "count": 8, |
| "is_parallel": true, |
| "self": 0.0027416319999247207 |
| } |
| } |
| }, |
| "UnityEnvironment.step": { |
| "total": 0.052093448999585235, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.0006928479988346226, |
| "children": { |
| "UnityEnvironment._generate_step_input": { |
| "total": 0.00046999000005598646, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.00046999000005598646 |
| }, |
| "communicator.exchange": { |
| "total": 0.04898321600012423, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.04898321600012423 |
| }, |
| "steps_from_proto": { |
| "total": 0.0019473950005703955, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.0006424249995689024, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 0.001304970001001493, |
| "count": 8, |
| "is_parallel": true, |
| "self": 0.001304970001001493 |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "UnityEnvironment.step": { |
| "total": 1262.0463692420199, |
| "count": 63921, |
| "is_parallel": true, |
| "self": 33.92574866710129, |
| "children": { |
| "UnityEnvironment._generate_step_input": { |
| "total": 23.477669706035158, |
| "count": 63921, |
| "is_parallel": true, |
| "self": 23.477669706035158 |
| }, |
| "communicator.exchange": { |
| "total": 1096.244794087007, |
| "count": 63921, |
| "is_parallel": true, |
| "self": 1096.244794087007 |
| }, |
| "steps_from_proto": { |
| "total": 108.39815678187642, |
| "count": 63921, |
| "is_parallel": true, |
| "self": 22.759134471085417, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 85.639022310791, |
| "count": 511368, |
| "is_parallel": true, |
| "self": 85.639022310791 |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "trainer_advance": { |
| "total": 664.3166894978831, |
| "count": 63922, |
| "self": 2.651621592664924, |
| "children": { |
| "process_trajectory": { |
| "total": 127.81992935421749, |
| "count": 63922, |
| "self": 127.59496558121828, |
| "children": { |
| "RLTrainer._checkpoint": { |
| "total": 0.22496377299921733, |
| "count": 2, |
| "self": 0.22496377299921733 |
| } |
| } |
| }, |
| "_update_policy": { |
| "total": 533.8451385510007, |
| "count": 452, |
| "self": 297.1886035689704, |
| "children": { |
| "TorchPPOOptimizer.update": { |
| "total": 236.65653498203028, |
| "count": 22785, |
| "self": 236.65653498203028 |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "trainer_threads": { |
| "total": 1.1350002750987187e-06, |
| "count": 1, |
| "self": 1.1350002750987187e-06 |
| }, |
| "TrainerController._save_models": { |
| "total": 0.10730746099943644, |
| "count": 1, |
| "self": 0.0013567509995482396, |
| "children": { |
| "RLTrainer._checkpoint": { |
| "total": 0.1059507099998882, |
| "count": 1, |
| "self": 0.1059507099998882 |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
