| { |
| "name": "root", |
| "gauges": { |
| "Pyramids.Policy.Entropy.mean": { |
| "value": 1.1308037042617798, |
| "min": 1.0398516654968262, |
| "max": 1.4295711517333984, |
| "count": 11 |
| }, |
| "Pyramids.Policy.Entropy.sum": { |
| "value": 33887.92578125, |
| "min": 31145.63671875, |
| "max": 43367.46875, |
| "count": 11 |
| }, |
| "Pyramids.Step.mean": { |
| "value": 329879.0, |
| "min": 29952.0, |
| "max": 329879.0, |
| "count": 11 |
| }, |
| "Pyramids.Step.sum": { |
| "value": 329879.0, |
| "min": 29952.0, |
| "max": 329879.0, |
| "count": 11 |
| }, |
| "Pyramids.Policy.ExtrinsicValueEstimate.mean": { |
| "value": -0.018549079075455666, |
| "min": -0.11526176333427429, |
| "max": 0.017504574730992317, |
| "count": 11 |
| }, |
| "Pyramids.Policy.ExtrinsicValueEstimate.sum": { |
| "value": -4.5074262619018555, |
| "min": -27.893346786499023, |
| "max": 4.148584365844727, |
| "count": 11 |
| }, |
| "Pyramids.Policy.RndValueEstimate.mean": { |
| "value": 0.02716442383825779, |
| "min": 0.02716442383825779, |
| "max": 0.4139914810657501, |
| "count": 11 |
| }, |
| "Pyramids.Policy.RndValueEstimate.sum": { |
| "value": 6.600955009460449, |
| "min": 6.600955009460449, |
| "max": 98.11598205566406, |
| "count": 11 |
| }, |
| "Pyramids.Losses.PolicyLoss.mean": { |
| "value": 0.06703679753914314, |
| "min": 0.06621039790661089, |
| "max": 0.0717391827910578, |
| "count": 11 |
| }, |
| "Pyramids.Losses.PolicyLoss.sum": { |
| "value": 0.938515165548004, |
| "min": 0.48714895678574394, |
| "max": 1.0043485590748091, |
| "count": 11 |
| }, |
| "Pyramids.Losses.ValueLoss.mean": { |
| "value": 0.00348817364891378, |
| "min": 0.001142571199744791, |
| "max": 0.008168606512899804, |
| "count": 11 |
| }, |
| "Pyramids.Losses.ValueLoss.sum": { |
| "value": 0.04883443108479292, |
| "min": 0.01521227236604492, |
| "max": 0.057180245590298634, |
| "count": 11 |
| }, |
| "Pyramids.Policy.LearningRate.mean": { |
| "value": 0.00020564836002198573, |
| "min": 0.00020564836002198573, |
| "max": 0.00029515063018788575, |
| "count": 11 |
| }, |
| "Pyramids.Policy.LearningRate.sum": { |
| "value": 0.0028790770403078004, |
| "min": 0.0020660544113152, |
| "max": 0.0036331408889531, |
| "count": 11 |
| }, |
| "Pyramids.Policy.Epsilon.mean": { |
| "value": 0.16854944285714282, |
| "min": 0.16854944285714282, |
| "max": 0.19838354285714285, |
| "count": 11 |
| }, |
| "Pyramids.Policy.Epsilon.sum": { |
| "value": 2.3596921999999996, |
| "min": 1.3886848, |
| "max": 2.6110469, |
| "count": 11 |
| }, |
| "Pyramids.Policy.Beta.mean": { |
| "value": 0.006858089341428572, |
| "min": 0.006858089341428572, |
| "max": 0.00983851593142857, |
| "count": 11 |
| }, |
| "Pyramids.Policy.Beta.sum": { |
| "value": 0.09601325078000002, |
| "min": 0.06886961152, |
| "max": 0.12112358530999999, |
| "count": 11 |
| }, |
| "Pyramids.Losses.RNDLoss.mean": { |
| "value": 0.024172518402338028, |
| "min": 0.024172518402338028, |
| "max": 0.4678037166595459, |
| "count": 11 |
| }, |
| "Pyramids.Losses.RNDLoss.sum": { |
| "value": 0.338415265083313, |
| "min": 0.338415265083313, |
| "max": 3.2746260166168213, |
| "count": 11 |
| }, |
| "Pyramids.Environment.EpisodeLength.mean": { |
| "value": 883.65625, |
| "min": 883.65625, |
| "max": 999.0, |
| "count": 11 |
| }, |
| "Pyramids.Environment.EpisodeLength.sum": { |
| "value": 28277.0, |
| "min": 15984.0, |
| "max": 33386.0, |
| "count": 11 |
| }, |
| "Pyramids.Environment.CumulativeReward.mean": { |
| "value": -0.3215375440195203, |
| "min": -1.0000000521540642, |
| "max": -0.3215375440195203, |
| "count": 11 |
| }, |
| "Pyramids.Environment.CumulativeReward.sum": { |
| "value": -10.289201408624649, |
| "min": -29.418001741170883, |
| "max": -10.289201408624649, |
| "count": 11 |
| }, |
| "Pyramids.Policy.ExtrinsicReward.mean": { |
| "value": -0.3215375440195203, |
| "min": -1.0000000521540642, |
| "max": -0.3215375440195203, |
| "count": 11 |
| }, |
| "Pyramids.Policy.ExtrinsicReward.sum": { |
| "value": -10.289201408624649, |
| "min": -29.418001741170883, |
| "max": -10.289201408624649, |
| "count": 11 |
| }, |
| "Pyramids.Policy.RndReward.mean": { |
| "value": 0.22664340073242784, |
| "min": 0.22664340073242784, |
| "max": 10.145370788872242, |
| "count": 11 |
| }, |
| "Pyramids.Policy.RndReward.sum": { |
| "value": 7.252588823437691, |
| "min": 7.242296002805233, |
| "max": 162.32593262195587, |
| "count": 11 |
| }, |
| "Pyramids.IsTraining.mean": { |
| "value": 1.0, |
| "min": 1.0, |
| "max": 1.0, |
| "count": 11 |
| }, |
| "Pyramids.IsTraining.sum": { |
| "value": 1.0, |
| "min": 1.0, |
| "max": 1.0, |
| "count": 11 |
| } |
| }, |
| "metadata": { |
| "timer_format_version": "0.1.0", |
| "start_time_seconds": "1718824099", |
| "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]", |
| "command_line_arguments": "/usr/local/bin/mlagents-learn /content/ml-agents/config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics --force", |
| "mlagents_version": "1.1.0.dev0", |
| "mlagents_envs_version": "1.1.0.dev0", |
| "communication_protocol_version": "1.5.0", |
| "pytorch_version": "2.3.0+cu121", |
| "numpy_version": "1.23.5", |
| "end_time_seconds": "1718825220" |
| }, |
| "total": 1121.0809393199997, |
| "count": 1, |
| "self": 0.4026389040009235, |
| "children": { |
| "run_training.setup": { |
| "total": 0.07447329199931119, |
| "count": 1, |
| "self": 0.07447329199931119 |
| }, |
| "TrainerController.start_learning": { |
| "total": 1120.6038271239995, |
| "count": 1, |
| "self": 0.7882218019931315, |
| "children": { |
| "TrainerController._reset_env": { |
| "total": 3.156991851999919, |
| "count": 1, |
| "self": 3.156991851999919 |
| }, |
| "TrainerController.advance": { |
| "total": 1116.4269058950067, |
| "count": 21569, |
| "self": 0.8995950239705053, |
| "children": { |
| "env_step": { |
| "total": 715.2752966839826, |
| "count": 21569, |
| "self": 652.419127857107, |
| "children": { |
| "SubprocessEnvManager._take_step": { |
| "total": 62.36315696294423, |
| "count": 21569, |
| "self": 2.7653587229369805, |
| "children": { |
| "TorchPolicy.evaluate": { |
| "total": 59.59779824000725, |
| "count": 21407, |
| "self": 59.59779824000725 |
| } |
| } |
| }, |
| "workers": { |
| "total": 0.493011863931315, |
| "count": 21568, |
| "self": 0.0, |
| "children": { |
| "worker_root": { |
| "total": 1117.8726802580586, |
| "count": 21568, |
| "is_parallel": true, |
| "self": 533.2390788240909, |
| "children": { |
| "run_training.setup": { |
| "total": 0.0, |
| "count": 0, |
| "is_parallel": true, |
| "self": 0.0, |
| "children": { |
| "steps_from_proto": { |
| "total": 0.0032746819997555576, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.0010501700007807813, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 0.0022245119989747764, |
| "count": 8, |
| "is_parallel": true, |
| "self": 0.0022245119989747764 |
| } |
| } |
| }, |
| "UnityEnvironment.step": { |
| "total": 0.06598024100003386, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.0007907359995442675, |
| "children": { |
| "UnityEnvironment._generate_step_input": { |
| "total": 0.0005836860000272281, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.0005836860000272281 |
| }, |
| "communicator.exchange": { |
| "total": 0.06251860199972725, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.06251860199972725 |
| }, |
| "steps_from_proto": { |
| "total": 0.0020872170007351087, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.0004451500008144649, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 0.0016420669999206439, |
| "count": 8, |
| "is_parallel": true, |
| "self": 0.0016420669999206439 |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "UnityEnvironment.step": { |
| "total": 584.6336014339677, |
| "count": 21567, |
| "is_parallel": true, |
| "self": 18.131345316946863, |
| "children": { |
| "UnityEnvironment._generate_step_input": { |
| "total": 11.108870893032872, |
| "count": 21567, |
| "is_parallel": true, |
| "self": 11.108870893032872 |
| }, |
| "communicator.exchange": { |
| "total": 509.26788400898204, |
| "count": 21567, |
| "is_parallel": true, |
| "self": 509.26788400898204 |
| }, |
| "steps_from_proto": { |
| "total": 46.1255012150059, |
| "count": 21567, |
| "is_parallel": true, |
| "self": 9.9612487092827, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 36.1642525057232, |
| "count": 172536, |
| "is_parallel": true, |
| "self": 36.1642525057232 |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "trainer_advance": { |
| "total": 400.25201418705365, |
| "count": 21568, |
| "self": 1.4449834341075984, |
| "children": { |
| "process_trajectory": { |
| "total": 61.19179011894357, |
| "count": 21568, |
| "self": 61.19179011894357 |
| }, |
| "_update_policy": { |
| "total": 337.6152406340025, |
| "count": 143, |
| "self": 133.15822928901707, |
| "children": { |
| "TorchPPOOptimizer.update": { |
| "total": 204.4570113449854, |
| "count": 7809, |
| "self": 204.4570113449854 |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "trainer_threads": { |
| "total": 1.5180003174464218e-06, |
| "count": 1, |
| "self": 1.5180003174464218e-06 |
| }, |
| "TrainerController._save_models": { |
| "total": 0.23170605699942826, |
| "count": 1, |
| "self": 0.0029494599993995507, |
| "children": { |
| "RLTrainer._checkpoint": { |
| "total": 0.2287565970000287, |
| "count": 1, |
| "self": 0.2287565970000287 |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
