| { |
| "name": "root", |
| "gauges": { |
| "Pyramids.Policy.Entropy.mean": { |
| "value": 0.20883840322494507, |
| "min": 0.19934269785881042, |
| "max": 1.4834659099578857, |
| "count": 100 |
| }, |
| "Pyramids.Policy.Entropy.sum": { |
| "value": 6305.2490234375, |
| "min": 5968.60498046875, |
| "max": 45002.421875, |
| "count": 100 |
| }, |
| "Pyramids.Step.mean": { |
| "value": 2999875.0, |
| "min": 29952.0, |
| "max": 2999875.0, |
| "count": 100 |
| }, |
| "Pyramids.Step.sum": { |
| "value": 2999875.0, |
| "min": 29952.0, |
| "max": 2999875.0, |
| "count": 100 |
| }, |
| "Pyramids.Policy.ExtrinsicValueEstimate.mean": { |
| "value": 0.798509418964386, |
| "min": -0.08498506247997284, |
| "max": 0.8286927938461304, |
| "count": 100 |
| }, |
| "Pyramids.Policy.ExtrinsicValueEstimate.sum": { |
| "value": 242.7468719482422, |
| "min": -20.56638526916504, |
| "max": 249.4365234375, |
| "count": 100 |
| }, |
| "Pyramids.Policy.RndValueEstimate.mean": { |
| "value": 0.00782564003020525, |
| "min": -0.02389027550816536, |
| "max": 0.3482888638973236, |
| "count": 100 |
| }, |
| "Pyramids.Policy.RndValueEstimate.sum": { |
| "value": 2.3789947032928467, |
| "min": -6.2114715576171875, |
| "max": 83.58932495117188, |
| "count": 100 |
| }, |
| "Pyramids.Losses.PolicyLoss.mean": { |
| "value": 0.0685256353345245, |
| "min": 0.06373710363663525, |
| "max": 0.07483905499980742, |
| "count": 100 |
| }, |
| "Pyramids.Losses.PolicyLoss.sum": { |
| "value": 0.9593588946833431, |
| "min": 0.48028539652994195, |
| "max": 1.1069516701362434, |
| "count": 100 |
| }, |
| "Pyramids.Losses.ValueLoss.mean": { |
| "value": 0.015294011145929936, |
| "min": 0.000883022911804011, |
| "max": 0.016372764399125182, |
| "count": 100 |
| }, |
| "Pyramids.Losses.ValueLoss.sum": { |
| "value": 0.21411615604301912, |
| "min": 0.010596274941648132, |
| "max": 0.233787051406027, |
| "count": 100 |
| }, |
| "Pyramids.Policy.LearningRate.mean": { |
| "value": 1.506463783592856e-06, |
| "min": 1.506463783592856e-06, |
| "max": 0.00029838354339596195, |
| "count": 100 |
| }, |
| "Pyramids.Policy.LearningRate.sum": { |
| "value": 2.1090492970299984e-05, |
| "min": 2.1090492970299984e-05, |
| "max": 0.004072358742547132, |
| "count": 100 |
| }, |
| "Pyramids.Policy.Epsilon.mean": { |
| "value": 0.10050212142857143, |
| "min": 0.10050212142857143, |
| "max": 0.19946118095238097, |
| "count": 100 |
| }, |
| "Pyramids.Policy.Epsilon.sum": { |
| "value": 1.4070297, |
| "min": 1.3897045333333333, |
| "max": 2.8574528666666668, |
| "count": 100 |
| }, |
| "Pyramids.Policy.Beta.mean": { |
| "value": 6.016193071428568e-05, |
| "min": 6.016193071428568e-05, |
| "max": 0.009946171977142856, |
| "count": 100 |
| }, |
| "Pyramids.Policy.Beta.sum": { |
| "value": 0.0008422670299999995, |
| "min": 0.0008422670299999995, |
| "max": 0.13575954138, |
| "count": 100 |
| }, |
| "Pyramids.Losses.RNDLoss.mean": { |
| "value": 0.004812297411262989, |
| "min": 0.004657533951103687, |
| "max": 0.5557369589805603, |
| "count": 100 |
| }, |
| "Pyramids.Losses.RNDLoss.sum": { |
| "value": 0.067372165620327, |
| "min": 0.06520547717809677, |
| "max": 3.8901588916778564, |
| "count": 100 |
| }, |
| "Pyramids.Environment.EpisodeLength.mean": { |
| "value": 249.46031746031747, |
| "min": 213.3014705882353, |
| "max": 999.0, |
| "count": 100 |
| }, |
| "Pyramids.Environment.EpisodeLength.sum": { |
| "value": 31432.0, |
| "min": 15984.0, |
| "max": 32312.0, |
| "count": 100 |
| }, |
| "Pyramids.Environment.CumulativeReward.mean": { |
| "value": 1.7187904574804835, |
| "min": -1.0000000521540642, |
| "max": 1.7798248023664864, |
| "count": 100 |
| }, |
| "Pyramids.Environment.CumulativeReward.sum": { |
| "value": 216.56759764254093, |
| "min": -32.000001668930054, |
| "max": 243.83599792420864, |
| "count": 100 |
| }, |
| "Pyramids.Policy.ExtrinsicReward.mean": { |
| "value": 1.7187904574804835, |
| "min": -1.0000000521540642, |
| "max": 1.7798248023664864, |
| "count": 100 |
| }, |
| "Pyramids.Policy.ExtrinsicReward.sum": { |
| "value": 216.56759764254093, |
| "min": -32.000001668930054, |
| "max": 243.83599792420864, |
| "count": 100 |
| }, |
| "Pyramids.Policy.RndReward.mean": { |
| "value": 0.012556998638342882, |
| "min": 0.010937422458509365, |
| "max": 12.201441258192062, |
| "count": 100 |
| }, |
| "Pyramids.Policy.RndReward.sum": { |
| "value": 1.582181828431203, |
| "min": 1.426591651084891, |
| "max": 195.223060131073, |
| "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": "1699953005", |
| "python_version": "3.10.3 (main, Mar 28 2022, 09:30:03) [GCC 7.5.0]", |
| "command_line_arguments": "/home/yzeng/anaconda3/envs/deeprl_course_unit5/bin/mlagents-learn ../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": "2.1.0+cu121", |
| "numpy_version": "1.23.5", |
| "end_time_seconds": "1699956693" |
| }, |
| "total": 3688.2422509463504, |
| "count": 1, |
| "self": 0.3199370610527694, |
| "children": { |
| "run_training.setup": { |
| "total": 0.01085307402536273, |
| "count": 1, |
| "self": 0.01085307402536273 |
| }, |
| "TrainerController.start_learning": { |
| "total": 3687.9114608112723, |
| "count": 1, |
| "self": 3.372778186108917, |
| "children": { |
| "TrainerController._reset_env": { |
| "total": 0.8616877705790102, |
| "count": 1, |
| "self": 0.8616877705790102 |
| }, |
| "TrainerController.advance": { |
| "total": 3683.61380162742, |
| "count": 194507, |
| "self": 3.364317771513015, |
| "children": { |
| "env_step": { |
| "total": 2322.2837941045873, |
| "count": 194507, |
| "self": 2124.274842475541, |
| "children": { |
| "SubprocessEnvManager._take_step": { |
| "total": 195.91820556716993, |
| "count": 194507, |
| "self": 9.23077730787918, |
| "children": { |
| "TorchPolicy.evaluate": { |
| "total": 186.68742825929075, |
| "count": 187562, |
| "self": 186.68742825929075 |
| } |
| } |
| }, |
| "workers": { |
| "total": 2.090746061876416, |
| "count": 194507, |
| "self": 0.0, |
| "children": { |
| "worker_root": { |
| "total": 3683.273943124339, |
| "count": 194507, |
| "is_parallel": true, |
| "self": 1784.8197832303122, |
| "children": { |
| "run_training.setup": { |
| "total": 0.0, |
| "count": 0, |
| "is_parallel": true, |
| "self": 0.0, |
| "children": { |
| "steps_from_proto": { |
| "total": 0.0012163030914962292, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.0003676139749586582, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 0.000848689116537571, |
| "count": 8, |
| "is_parallel": true, |
| "self": 0.000848689116537571 |
| } |
| } |
| }, |
| "UnityEnvironment.step": { |
| "total": 0.023782378993928432, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.00025271298363804817, |
| "children": { |
| "UnityEnvironment._generate_step_input": { |
| "total": 0.00029502203688025475, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.00029502203688025475 |
| }, |
| "communicator.exchange": { |
| "total": 0.02243240363895893, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.02243240363895893 |
| }, |
| "steps_from_proto": { |
| "total": 0.0008022403344511986, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.0001949523575603962, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 0.0006072879768908024, |
| "count": 8, |
| "is_parallel": true, |
| "self": 0.0006072879768908024 |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "UnityEnvironment.step": { |
| "total": 1898.4541598940268, |
| "count": 194506, |
| "is_parallel": true, |
| "self": 53.04335350031033, |
| "children": { |
| "UnityEnvironment._generate_step_input": { |
| "total": 39.29772320250049, |
| "count": 194506, |
| "is_parallel": true, |
| "self": 39.29772320250049 |
| }, |
| "communicator.exchange": { |
| "total": 1648.587595764082, |
| "count": 194506, |
| "is_parallel": true, |
| "self": 1648.587595764082 |
| }, |
| "steps_from_proto": { |
| "total": 157.52548742713407, |
| "count": 194506, |
| "is_parallel": true, |
| "self": 36.79078872175887, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 120.7346987053752, |
| "count": 1556048, |
| "is_parallel": true, |
| "self": 120.7346987053752 |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "trainer_advance": { |
| "total": 1357.9656897513196, |
| "count": 194507, |
| "self": 6.280239996500313, |
| "children": { |
| "process_trajectory": { |
| "total": 229.36559143615887, |
| "count": 194507, |
| "self": 228.95419924287125, |
| "children": { |
| "RLTrainer._checkpoint": { |
| "total": 0.411392193287611, |
| "count": 6, |
| "self": 0.411392193287611 |
| } |
| } |
| }, |
| "_update_policy": { |
| "total": 1122.3198583186604, |
| "count": 1396, |
| "self": 592.612791213207, |
| "children": { |
| "TorchPPOOptimizer.update": { |
| "total": 529.7070671054535, |
| "count": 68406, |
| "self": 529.7070671054535 |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "trainer_threads": { |
| "total": 9.122304618358612e-07, |
| "count": 1, |
| "self": 9.122304618358612e-07 |
| }, |
| "TrainerController._save_models": { |
| "total": 0.06319231493398547, |
| "count": 1, |
| "self": 0.0008483538404107094, |
| "children": { |
| "RLTrainer._checkpoint": { |
| "total": 0.06234396109357476, |
| "count": 1, |
| "self": 0.06234396109357476 |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
