| { |
| "name": "root", |
| "gauges": { |
| "Pyramids.Policy.Entropy.mean": { |
| "value": 0.8549647331237793, |
| "min": 0.8549647331237793, |
| "max": 1.506505012512207, |
| "count": 16 |
| }, |
| "Pyramids.Policy.Entropy.sum": { |
| "value": 25635.26171875, |
| "min": 25635.26171875, |
| "max": 45701.3359375, |
| "count": 16 |
| }, |
| "Pyramids.Step.mean": { |
| "value": 479987.0, |
| "min": 29952.0, |
| "max": 479987.0, |
| "count": 16 |
| }, |
| "Pyramids.Step.sum": { |
| "value": 479987.0, |
| "min": 29952.0, |
| "max": 479987.0, |
| "count": 16 |
| }, |
| "Pyramids.Policy.ExtrinsicValueEstimate.mean": { |
| "value": -0.069112628698349, |
| "min": -0.11863730102777481, |
| "max": -0.021677853539586067, |
| "count": 16 |
| }, |
| "Pyramids.Policy.ExtrinsicValueEstimate.sum": { |
| "value": -16.794368743896484, |
| "min": -28.117040634155273, |
| "max": -5.267718315124512, |
| "count": 16 |
| }, |
| "Pyramids.Policy.RndValueEstimate.mean": { |
| "value": 0.019834093749523163, |
| "min": 0.019834093749523163, |
| "max": 0.29595303535461426, |
| "count": 16 |
| }, |
| "Pyramids.Policy.RndValueEstimate.sum": { |
| "value": 4.819684982299805, |
| "min": 4.819684982299805, |
| "max": 70.140869140625, |
| "count": 16 |
| }, |
| "Pyramids.Losses.PolicyLoss.mean": { |
| "value": 0.0659549054564567, |
| "min": 0.06528209482607593, |
| "max": 0.0751006422591057, |
| "count": 16 |
| }, |
| "Pyramids.Losses.PolicyLoss.sum": { |
| "value": 0.9233686763903939, |
| "min": 0.4788473356502122, |
| "max": 0.9855747316745976, |
| "count": 16 |
| }, |
| "Pyramids.Losses.ValueLoss.mean": { |
| "value": 0.001681840885257783, |
| "min": 0.0003594376103292175, |
| "max": 0.005031318694938239, |
| "count": 16 |
| }, |
| "Pyramids.Losses.ValueLoss.sum": { |
| "value": 0.023545772393608964, |
| "min": 0.00431325132395061, |
| "max": 0.050746901483387986, |
| "count": 16 |
| }, |
| "Pyramids.Policy.LearningRate.mean": { |
| "value": 2.1240264348514283e-05, |
| "min": 2.1240264348514283e-05, |
| "max": 0.00029030126037577137, |
| "count": 16 |
| }, |
| "Pyramids.Policy.LearningRate.sum": { |
| "value": 0.0002973637008792, |
| "min": 0.0002973637008792, |
| "max": 0.0026341275219576004, |
| "count": 16 |
| }, |
| "Pyramids.Policy.Epsilon.mean": { |
| "value": 0.10708005714285716, |
| "min": 0.10708005714285716, |
| "max": 0.19676708571428575, |
| "count": 16 |
| }, |
| "Pyramids.Policy.Epsilon.sum": { |
| "value": 1.4991208000000003, |
| "min": 1.3773696000000002, |
| "max": 2.0938972, |
| "count": 16 |
| }, |
| "Pyramids.Policy.Beta.mean": { |
| "value": 0.0007172977085714287, |
| "min": 0.0007172977085714287, |
| "max": 0.00967703186285714, |
| "count": 16 |
| }, |
| "Pyramids.Policy.Beta.sum": { |
| "value": 0.010042167920000003, |
| "min": 0.010042167920000003, |
| "max": 0.08783643575999998, |
| "count": 16 |
| }, |
| "Pyramids.Losses.RNDLoss.mean": { |
| "value": 0.019233208149671555, |
| "min": 0.019233208149671555, |
| "max": 0.37762317061424255, |
| "count": 16 |
| }, |
| "Pyramids.Losses.RNDLoss.sum": { |
| "value": 0.26926490664482117, |
| "min": 0.26926490664482117, |
| "max": 2.643362283706665, |
| "count": 16 |
| }, |
| "Pyramids.Environment.EpisodeLength.mean": { |
| "value": 918.3333333333334, |
| "min": 910.96, |
| "max": 999.0, |
| "count": 16 |
| }, |
| "Pyramids.Environment.EpisodeLength.sum": { |
| "value": 30305.0, |
| "min": 15984.0, |
| "max": 32736.0, |
| "count": 16 |
| }, |
| "Pyramids.Environment.CumulativeReward.mean": { |
| "value": -0.6765697424610456, |
| "min": -1.0000000521540642, |
| "max": -0.5115600454807282, |
| "count": 16 |
| }, |
| "Pyramids.Environment.CumulativeReward.sum": { |
| "value": -22.326801501214504, |
| "min": -31.9992016851902, |
| "max": -12.789001137018204, |
| "count": 16 |
| }, |
| "Pyramids.Policy.ExtrinsicReward.mean": { |
| "value": -0.6765697424610456, |
| "min": -1.0000000521540642, |
| "max": -0.5115600454807282, |
| "count": 16 |
| }, |
| "Pyramids.Policy.ExtrinsicReward.sum": { |
| "value": -22.326801501214504, |
| "min": -31.9992016851902, |
| "max": -12.789001137018204, |
| "count": 16 |
| }, |
| "Pyramids.Policy.RndReward.mean": { |
| "value": 0.18421179889419087, |
| "min": 0.18421179889419087, |
| "max": 8.230333052575588, |
| "count": 16 |
| }, |
| "Pyramids.Policy.RndReward.sum": { |
| "value": 6.078989363508299, |
| "min": 6.078989363508299, |
| "max": 131.6853288412094, |
| "count": 16 |
| }, |
| "Pyramids.IsTraining.mean": { |
| "value": 1.0, |
| "min": 1.0, |
| "max": 1.0, |
| "count": 16 |
| }, |
| "Pyramids.IsTraining.sum": { |
| "value": 1.0, |
| "min": 1.0, |
| "max": 1.0, |
| "count": 16 |
| } |
| }, |
| "metadata": { |
| "timer_format_version": "0.1.0", |
| "start_time_seconds": "1746790230", |
| "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": "2.7.0+cu126", |
| "numpy_version": "1.23.5", |
| "end_time_seconds": "1746791372" |
| }, |
| "total": 1142.473794465, |
| "count": 1, |
| "self": 0.490108907999911, |
| "children": { |
| "run_training.setup": { |
| "total": 0.021556549000251835, |
| "count": 1, |
| "self": 0.021556549000251835 |
| }, |
| "TrainerController.start_learning": { |
| "total": 1141.962129008, |
| "count": 1, |
| "self": 0.7169487809428574, |
| "children": { |
| "TrainerController._reset_env": { |
| "total": 2.3759234240001206, |
| "count": 1, |
| "self": 2.3759234240001206 |
| }, |
| "TrainerController.advance": { |
| "total": 1138.7617848570571, |
| "count": 31516, |
| "self": 0.7508249781153609, |
| "children": { |
| "env_step": { |
| "total": 786.8222813759489, |
| "count": 31516, |
| "self": 705.4419411999679, |
| "children": { |
| "SubprocessEnvManager._take_step": { |
| "total": 80.97741033197099, |
| "count": 31516, |
| "self": 2.5149954279850135, |
| "children": { |
| "TorchPolicy.evaluate": { |
| "total": 78.46241490398597, |
| "count": 31328, |
| "self": 78.46241490398597 |
| } |
| } |
| }, |
| "workers": { |
| "total": 0.40292984401003196, |
| "count": 31516, |
| "self": 0.0, |
| "children": { |
| "worker_root": { |
| "total": 1139.2787704829793, |
| "count": 31516, |
| "is_parallel": true, |
| "self": 494.1346449929888, |
| "children": { |
| "run_training.setup": { |
| "total": 0.0, |
| "count": 0, |
| "is_parallel": true, |
| "self": 0.0, |
| "children": { |
| "steps_from_proto": { |
| "total": 0.0020576900001287868, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.0007015510000201175, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 0.0013561390001086693, |
| "count": 8, |
| "is_parallel": true, |
| "self": 0.0013561390001086693 |
| } |
| } |
| }, |
| "UnityEnvironment.step": { |
| "total": 0.05361804399990433, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.0005673389996445621, |
| "children": { |
| "UnityEnvironment._generate_step_input": { |
| "total": 0.0005635540001094341, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.0005635540001094341 |
| }, |
| "communicator.exchange": { |
| "total": 0.050792396000360895, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.050792396000360895 |
| }, |
| "steps_from_proto": { |
| "total": 0.0016947549997894384, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.00035731599973587436, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 0.001337439000053564, |
| "count": 8, |
| "is_parallel": true, |
| "self": 0.001337439000053564 |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "UnityEnvironment.step": { |
| "total": 645.1441254899905, |
| "count": 31515, |
| "is_parallel": true, |
| "self": 16.668768702934358, |
| "children": { |
| "UnityEnvironment._generate_step_input": { |
| "total": 12.508553180001854, |
| "count": 31515, |
| "is_parallel": true, |
| "self": 12.508553180001854 |
| }, |
| "communicator.exchange": { |
| "total": 563.6510853640311, |
| "count": 31515, |
| "is_parallel": true, |
| "self": 563.6510853640311 |
| }, |
| "steps_from_proto": { |
| "total": 52.315718243023184, |
| "count": 31515, |
| "is_parallel": true, |
| "self": 10.644815382088382, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 41.6709028609348, |
| "count": 252120, |
| "is_parallel": true, |
| "self": 41.6709028609348 |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "trainer_advance": { |
| "total": 351.18867850299284, |
| "count": 31516, |
| "self": 1.1732564339840792, |
| "children": { |
| "process_trajectory": { |
| "total": 67.52694380901039, |
| "count": 31516, |
| "self": 67.40264100201057, |
| "children": { |
| "RLTrainer._checkpoint": { |
| "total": 0.12430280699982177, |
| "count": 1, |
| "self": 0.12430280699982177 |
| } |
| } |
| }, |
| "_update_policy": { |
| "total": 282.4884782599984, |
| "count": 206, |
| "self": 158.77124386200876, |
| "children": { |
| "TorchPPOOptimizer.update": { |
| "total": 123.71723439798961, |
| "count": 11493, |
| "self": 123.71723439798961 |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "trainer_threads": { |
| "total": 1.1229999472561758e-06, |
| "count": 1, |
| "self": 1.1229999472561758e-06 |
| }, |
| "TrainerController._save_models": { |
| "total": 0.10747082299985777, |
| "count": 1, |
| "self": 0.0010965869996653055, |
| "children": { |
| "RLTrainer._checkpoint": { |
| "total": 0.10637423600019247, |
| "count": 1, |
| "self": 0.10637423600019247 |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
