| { |
| "name": "root", |
| "gauges": { |
| "Pyramids.Policy.Entropy.mean": { |
| "value": 0.15378352999687195, |
| "min": 0.14064596593379974, |
| "max": 1.4660212993621826, |
| "count": 100 |
| }, |
| "Pyramids.Policy.Entropy.sum": { |
| "value": 4638.111328125, |
| "min": 4194.62548828125, |
| "max": 44473.22265625, |
| "count": 100 |
| }, |
| "Pyramids.Step.mean": { |
| "value": 2999872.0, |
| "min": 29952.0, |
| "max": 2999872.0, |
| "count": 100 |
| }, |
| "Pyramids.Step.sum": { |
| "value": 2999872.0, |
| "min": 29952.0, |
| "max": 2999872.0, |
| "count": 100 |
| }, |
| "Pyramids.Policy.ExtrinsicValueEstimate.mean": { |
| "value": 0.8294541239738464, |
| "min": -0.10551862418651581, |
| "max": 0.8681994080543518, |
| "count": 100 |
| }, |
| "Pyramids.Policy.ExtrinsicValueEstimate.sum": { |
| "value": 253.81295776367188, |
| "min": -25.32447052001953, |
| "max": 263.0644226074219, |
| "count": 100 |
| }, |
| "Pyramids.Policy.RndValueEstimate.mean": { |
| "value": 0.01605323702096939, |
| "min": -0.02165089175105095, |
| "max": 0.27688130736351013, |
| "count": 100 |
| }, |
| "Pyramids.Policy.RndValueEstimate.sum": { |
| "value": 4.912290573120117, |
| "min": -6.300409317016602, |
| "max": 67.28215789794922, |
| "count": 100 |
| }, |
| "Pyramids.Losses.PolicyLoss.mean": { |
| "value": 0.07083913966312584, |
| "min": 0.06442113338609749, |
| "max": 0.07348860550527683, |
| "count": 100 |
| }, |
| "Pyramids.Losses.PolicyLoss.sum": { |
| "value": 0.9917479552837618, |
| "min": 0.49137666816884235, |
| "max": 1.078233029954729, |
| "count": 100 |
| }, |
| "Pyramids.Losses.ValueLoss.mean": { |
| "value": 0.013722563465631304, |
| "min": 0.00013341782571683818, |
| "max": 0.016837581999078838, |
| "count": 100 |
| }, |
| "Pyramids.Losses.ValueLoss.sum": { |
| "value": 0.19211588851883826, |
| "min": 0.0017344317343188963, |
| "max": 0.23572614798710373, |
| "count": 100 |
| }, |
| "Pyramids.Policy.LearningRate.mean": { |
| "value": 1.582506615388096e-06, |
| "min": 1.582506615388096e-06, |
| "max": 0.00029838354339596195, |
| "count": 100 |
| }, |
| "Pyramids.Policy.LearningRate.sum": { |
| "value": 2.2155092615433342e-05, |
| "min": 2.2155092615433342e-05, |
| "max": 0.004052940949019699, |
| "count": 100 |
| }, |
| "Pyramids.Policy.Epsilon.mean": { |
| "value": 0.10052746904761907, |
| "min": 0.10052746904761907, |
| "max": 0.19946118095238097, |
| "count": 100 |
| }, |
| "Pyramids.Policy.Epsilon.sum": { |
| "value": 1.407384566666667, |
| "min": 1.3962282666666668, |
| "max": 2.8425251666666673, |
| "count": 100 |
| }, |
| "Pyramids.Policy.Beta.mean": { |
| "value": 6.269415785714289e-05, |
| "min": 6.269415785714289e-05, |
| "max": 0.009946171977142856, |
| "count": 100 |
| }, |
| "Pyramids.Policy.Beta.sum": { |
| "value": 0.0008777182100000006, |
| "min": 0.0008777182100000006, |
| "max": 0.13510293196999998, |
| "count": 100 |
| }, |
| "Pyramids.Losses.RNDLoss.mean": { |
| "value": 0.005908201914280653, |
| "min": 0.005729589611291885, |
| "max": 0.4693025052547455, |
| "count": 100 |
| }, |
| "Pyramids.Losses.RNDLoss.sum": { |
| "value": 0.08271482586860657, |
| "min": 0.0802142545580864, |
| "max": 3.2851176261901855, |
| "count": 100 |
| }, |
| "Pyramids.Environment.EpisodeLength.mean": { |
| "value": 210.83916083916083, |
| "min": 210.83916083916083, |
| "max": 999.0, |
| "count": 100 |
| }, |
| "Pyramids.Environment.EpisodeLength.sum": { |
| "value": 30150.0, |
| "min": 15984.0, |
| "max": 34476.0, |
| "count": 100 |
| }, |
| "Pyramids.Environment.CumulativeReward.mean": { |
| "value": 1.789160823280161, |
| "min": -1.0000000521540642, |
| "max": 1.789160823280161, |
| "count": 100 |
| }, |
| "Pyramids.Environment.CumulativeReward.sum": { |
| "value": 255.84999772906303, |
| "min": -30.994801610708237, |
| "max": 255.84999772906303, |
| "count": 100 |
| }, |
| "Pyramids.Policy.ExtrinsicReward.mean": { |
| "value": 1.789160823280161, |
| "min": -1.0000000521540642, |
| "max": 1.789160823280161, |
| "count": 100 |
| }, |
| "Pyramids.Policy.ExtrinsicReward.sum": { |
| "value": 255.84999772906303, |
| "min": -30.994801610708237, |
| "max": 255.84999772906303, |
| "count": 100 |
| }, |
| "Pyramids.Policy.RndReward.mean": { |
| "value": 0.013045026905013662, |
| "min": 0.013045026905013662, |
| "max": 9.668415855616331, |
| "count": 100 |
| }, |
| "Pyramids.Policy.RndReward.sum": { |
| "value": 1.8654388474169536, |
| "min": 1.6810851612390252, |
| "max": 154.6946536898613, |
| "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": "1700127557", |
| "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [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": "2.1.0+cu118", |
| "numpy_version": "1.23.5", |
| "end_time_seconds": "1700140292" |
| }, |
| "total": 12735.791693758, |
| "count": 1, |
| "self": 1.3507895239981735, |
| "children": { |
| "run_training.setup": { |
| "total": 0.06350711100003537, |
| "count": 1, |
| "self": 0.06350711100003537 |
| }, |
| "TrainerController.start_learning": { |
| "total": 12734.377397123, |
| "count": 1, |
| "self": 7.848981506047494, |
| "children": { |
| "TrainerController._reset_env": { |
| "total": 1.969111182000006, |
| "count": 1, |
| "self": 1.969111182000006 |
| }, |
| "TrainerController.advance": { |
| "total": 12724.435185411954, |
| "count": 195193, |
| "self": 9.313524021841658, |
| "children": { |
| "env_step": { |
| "total": 8792.905527942057, |
| "count": 195193, |
| "self": 8230.656015608749, |
| "children": { |
| "SubprocessEnvManager._take_step": { |
| "total": 557.4007865475262, |
| "count": 195193, |
| "self": 25.922084647347674, |
| "children": { |
| "TorchPolicy.evaluate": { |
| "total": 531.4787019001785, |
| "count": 187566, |
| "self": 531.4787019001785 |
| } |
| } |
| }, |
| "workers": { |
| "total": 4.848725785781426, |
| "count": 195193, |
| "self": 0.0, |
| "children": { |
| "worker_root": { |
| "total": 12709.07262393727, |
| "count": 195193, |
| "is_parallel": true, |
| "self": 5102.826333066101, |
| "children": { |
| "run_training.setup": { |
| "total": 0.0, |
| "count": 0, |
| "is_parallel": true, |
| "self": 0.0, |
| "children": { |
| "steps_from_proto": { |
| "total": 0.0029109170000083395, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.0010478810002041428, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 0.0018630359998041968, |
| "count": 8, |
| "is_parallel": true, |
| "self": 0.0018630359998041968 |
| } |
| } |
| }, |
| "UnityEnvironment.step": { |
| "total": 0.06398659900014536, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.0007122920001165767, |
| "children": { |
| "UnityEnvironment._generate_step_input": { |
| "total": 0.0005405669999163365, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.0005405669999163365 |
| }, |
| "communicator.exchange": { |
| "total": 0.060743900000034046, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.060743900000034046 |
| }, |
| "steps_from_proto": { |
| "total": 0.0019898400000784022, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.00047563300017827714, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 0.001514206999900125, |
| "count": 8, |
| "is_parallel": true, |
| "self": 0.001514206999900125 |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "UnityEnvironment.step": { |
| "total": 7606.24629087117, |
| "count": 195192, |
| "is_parallel": true, |
| "self": 152.92823860721, |
| "children": { |
| "UnityEnvironment._generate_step_input": { |
| "total": 92.711893066725, |
| "count": 195192, |
| "is_parallel": true, |
| "self": 92.711893066725 |
| }, |
| "communicator.exchange": { |
| "total": 6926.769682427796, |
| "count": 195192, |
| "is_parallel": true, |
| "self": 6926.769682427796 |
| }, |
| "steps_from_proto": { |
| "total": 433.8364767694379, |
| "count": 195192, |
| "is_parallel": true, |
| "self": 95.34607191468308, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 338.49040485475484, |
| "count": 1561536, |
| "is_parallel": true, |
| "self": 338.49040485475484 |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "trainer_advance": { |
| "total": 3922.2161334480543, |
| "count": 195193, |
| "self": 16.70470839783775, |
| "children": { |
| "process_trajectory": { |
| "total": 581.2622050202403, |
| "count": 195193, |
| "self": 580.3757249082387, |
| "children": { |
| "RLTrainer._checkpoint": { |
| "total": 0.8864801120016637, |
| "count": 6, |
| "self": 0.8864801120016637 |
| } |
| } |
| }, |
| "_update_policy": { |
| "total": 3324.249220029976, |
| "count": 1405, |
| "self": 1329.3855336976992, |
| "children": { |
| "TorchPPOOptimizer.update": { |
| "total": 1994.863686332277, |
| "count": 68406, |
| "self": 1994.863686332277 |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "trainer_threads": { |
| "total": 1.3980006769998e-06, |
| "count": 1, |
| "self": 1.3980006769998e-06 |
| }, |
| "TrainerController._save_models": { |
| "total": 0.12411762499868928, |
| "count": 1, |
| "self": 0.0025717649987200275, |
| "children": { |
| "RLTrainer._checkpoint": { |
| "total": 0.12154585999996925, |
| "count": 1, |
| "self": 0.12154585999996925 |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
