| { |
| "name": "root", |
| "gauges": { |
| "Pyramids.Policy.Entropy.mean": { |
| "value": 0.31614795327186584, |
| "min": 0.3133101761341095, |
| "max": 1.4786099195480347, |
| "count": 33 |
| }, |
| "Pyramids.Policy.Entropy.sum": { |
| "value": 9438.9130859375, |
| "min": 9294.033203125, |
| "max": 44855.109375, |
| "count": 33 |
| }, |
| "Pyramids.Step.mean": { |
| "value": 989905.0, |
| "min": 29928.0, |
| "max": 989905.0, |
| "count": 33 |
| }, |
| "Pyramids.Step.sum": { |
| "value": 989905.0, |
| "min": 29928.0, |
| "max": 989905.0, |
| "count": 33 |
| }, |
| "Pyramids.Policy.ExtrinsicValueEstimate.mean": { |
| "value": 0.5344586372375488, |
| "min": -0.10325628519058228, |
| "max": 0.5344586372375488, |
| "count": 33 |
| }, |
| "Pyramids.Policy.ExtrinsicValueEstimate.sum": { |
| "value": 148.0450439453125, |
| "min": -24.884765625, |
| "max": 148.0450439453125, |
| "count": 33 |
| }, |
| "Pyramids.Policy.RndValueEstimate.mean": { |
| "value": 0.018666913732886314, |
| "min": -0.026318447664380074, |
| "max": 0.2914782166481018, |
| "count": 33 |
| }, |
| "Pyramids.Policy.RndValueEstimate.sum": { |
| "value": 5.1707353591918945, |
| "min": -7.132299423217773, |
| "max": 69.08033752441406, |
| "count": 33 |
| }, |
| "Pyramids.Losses.PolicyLoss.mean": { |
| "value": 0.06856968893650142, |
| "min": 0.06551236047914348, |
| "max": 0.07410694344712065, |
| "count": 33 |
| }, |
| "Pyramids.Losses.PolicyLoss.sum": { |
| "value": 0.95997564511102, |
| "min": 0.5744742576799031, |
| "max": 1.1000188456719295, |
| "count": 33 |
| }, |
| "Pyramids.Losses.ValueLoss.mean": { |
| "value": 0.015221073412768809, |
| "min": 0.00042303003547693874, |
| "max": 0.01620259309233266, |
| "count": 33 |
| }, |
| "Pyramids.Losses.ValueLoss.sum": { |
| "value": 0.21309502777876332, |
| "min": 0.005076360425723265, |
| "max": 0.22683630329265725, |
| "count": 33 |
| }, |
| "Pyramids.Policy.LearningRate.mean": { |
| "value": 7.257847580750001e-06, |
| "min": 7.257847580750001e-06, |
| "max": 0.0002952102015966, |
| "count": 33 |
| }, |
| "Pyramids.Policy.LearningRate.sum": { |
| "value": 0.00010160986613050001, |
| "min": 0.00010160986613050001, |
| "max": 0.0033821288726238003, |
| "count": 33 |
| }, |
| "Pyramids.Policy.Epsilon.mean": { |
| "value": 0.10241925, |
| "min": 0.10241925, |
| "max": 0.1984034, |
| "count": 33 |
| }, |
| "Pyramids.Policy.Epsilon.sum": { |
| "value": 1.4338695000000001, |
| "min": 1.4338695000000001, |
| "max": 2.5273762, |
| "count": 33 |
| }, |
| "Pyramids.Policy.Beta.mean": { |
| "value": 0.000251683075, |
| "min": 0.000251683075, |
| "max": 0.00984049966, |
| "count": 33 |
| }, |
| "Pyramids.Policy.Beta.sum": { |
| "value": 0.00352356305, |
| "min": 0.00352356305, |
| "max": 0.11276488238, |
| "count": 33 |
| }, |
| "Pyramids.Losses.RNDLoss.mean": { |
| "value": 0.011838098056614399, |
| "min": 0.011768247000873089, |
| "max": 0.37937092781066895, |
| "count": 33 |
| }, |
| "Pyramids.Losses.RNDLoss.sum": { |
| "value": 0.16573336720466614, |
| "min": 0.16573336720466614, |
| "max": 3.0349674224853516, |
| "count": 33 |
| }, |
| "Pyramids.Environment.EpisodeLength.mean": { |
| "value": 349.79787234042556, |
| "min": 349.79787234042556, |
| "max": 999.0, |
| "count": 33 |
| }, |
| "Pyramids.Environment.EpisodeLength.sum": { |
| "value": 32881.0, |
| "min": 15960.0, |
| "max": 32881.0, |
| "count": 33 |
| }, |
| "Pyramids.Environment.CumulativeReward.mean": { |
| "value": 1.5926515939094688, |
| "min": -0.9999750526621938, |
| "max": 1.6096999775140712, |
| "count": 33 |
| }, |
| "Pyramids.Environment.CumulativeReward.sum": { |
| "value": 148.1165982335806, |
| "min": -31.9992016851902, |
| "max": 148.1165982335806, |
| "count": 33 |
| }, |
| "Pyramids.Policy.ExtrinsicReward.mean": { |
| "value": 1.5926515939094688, |
| "min": -0.9999750526621938, |
| "max": 1.6096999775140712, |
| "count": 33 |
| }, |
| "Pyramids.Policy.ExtrinsicReward.sum": { |
| "value": 148.1165982335806, |
| "min": -31.9992016851902, |
| "max": 148.1165982335806, |
| "count": 33 |
| }, |
| "Pyramids.Policy.RndReward.mean": { |
| "value": 0.04206799990522565, |
| "min": 0.04206799990522565, |
| "max": 7.765598534606397, |
| "count": 33 |
| }, |
| "Pyramids.Policy.RndReward.sum": { |
| "value": 3.9123239911859855, |
| "min": 3.395062978961505, |
| "max": 124.24957655370235, |
| "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": "1683104108", |
| "python_version": "3.10.11 (main, Apr 5 2023, 14:15:10) [GCC 9.4.0]", |
| "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": "0.31.0.dev0", |
| "mlagents_envs_version": "0.31.0.dev0", |
| "communication_protocol_version": "1.5.0", |
| "pytorch_version": "1.11.0+cu102", |
| "numpy_version": "1.21.2", |
| "end_time_seconds": "1683107613" |
| }, |
| "total": 3504.563691634, |
| "count": 1, |
| "self": 0.6437886300000173, |
| "children": { |
| "run_training.setup": { |
| "total": 0.05805388299995684, |
| "count": 1, |
| "self": 0.05805388299995684 |
| }, |
| "TrainerController.start_learning": { |
| "total": 3503.861849121, |
| "count": 1, |
| "self": 2.3233595340057036, |
| "children": { |
| "TrainerController._reset_env": { |
| "total": 1.4399941530000433, |
| "count": 1, |
| "self": 1.4399941530000433 |
| }, |
| "TrainerController.advance": { |
| "total": 3499.975233230994, |
| "count": 63713, |
| "self": 2.3354660000782133, |
| "children": { |
| "env_step": { |
| "total": 2315.088577250976, |
| "count": 63713, |
| "self": 2171.8654195729623, |
| "children": { |
| "SubprocessEnvManager._take_step": { |
| "total": 141.8018996558967, |
| "count": 63713, |
| "self": 7.1924239678699, |
| "children": { |
| "TorchPolicy.evaluate": { |
| "total": 134.6094756880268, |
| "count": 62553, |
| "self": 134.6094756880268 |
| } |
| } |
| }, |
| "workers": { |
| "total": 1.4212580221169446, |
| "count": 63713, |
| "self": 0.0, |
| "children": { |
| "worker_root": { |
| "total": 3496.299039247917, |
| "count": 63713, |
| "is_parallel": true, |
| "self": 1499.2656022928513, |
| "children": { |
| "run_training.setup": { |
| "total": 0.0, |
| "count": 0, |
| "is_parallel": true, |
| "self": 0.0, |
| "children": { |
| "steps_from_proto": { |
| "total": 0.002761974999884842, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.0006400569996003469, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 0.002121918000284495, |
| "count": 8, |
| "is_parallel": true, |
| "self": 0.002121918000284495 |
| } |
| } |
| }, |
| "UnityEnvironment.step": { |
| "total": 0.11853186899998036, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.0006631400001424481, |
| "children": { |
| "UnityEnvironment._generate_step_input": { |
| "total": 0.0004887329998837231, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.0004887329998837231 |
| }, |
| "communicator.exchange": { |
| "total": 0.11522406699987187, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.11522406699987187 |
| }, |
| "steps_from_proto": { |
| "total": 0.002155929000082324, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.0003899770001680736, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 0.0017659519999142503, |
| "count": 8, |
| "is_parallel": true, |
| "self": 0.0017659519999142503 |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "UnityEnvironment.step": { |
| "total": 1997.0334369550656, |
| "count": 63712, |
| "is_parallel": true, |
| "self": 46.68469840389889, |
| "children": { |
| "UnityEnvironment._generate_step_input": { |
| "total": 27.003006118963867, |
| "count": 63712, |
| "is_parallel": true, |
| "self": 27.003006118963867 |
| }, |
| "communicator.exchange": { |
| "total": 1785.961976540006, |
| "count": 63712, |
| "is_parallel": true, |
| "self": 1785.961976540006 |
| }, |
| "steps_from_proto": { |
| "total": 137.38375589219686, |
| "count": 63712, |
| "is_parallel": true, |
| "self": 29.385367073937005, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 107.99838881825985, |
| "count": 509696, |
| "is_parallel": true, |
| "self": 107.99838881825985 |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "trainer_advance": { |
| "total": 1182.5511899799399, |
| "count": 63713, |
| "self": 4.577144052903577, |
| "children": { |
| "process_trajectory": { |
| "total": 150.1377383950453, |
| "count": 63713, |
| "self": 149.84522223804515, |
| "children": { |
| "RLTrainer._checkpoint": { |
| "total": 0.29251615700013645, |
| "count": 2, |
| "self": 0.29251615700013645 |
| } |
| } |
| }, |
| "_update_policy": { |
| "total": 1027.836307531991, |
| "count": 453, |
| "self": 425.7108885999826, |
| "children": { |
| "TorchPPOOptimizer.update": { |
| "total": 602.1254189320084, |
| "count": 22890, |
| "self": 602.1254189320084 |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "trainer_threads": { |
| "total": 1.3250000847619958e-06, |
| "count": 1, |
| "self": 1.3250000847619958e-06 |
| }, |
| "TrainerController._save_models": { |
| "total": 0.1232608780001101, |
| "count": 1, |
| "self": 0.002079774000776524, |
| "children": { |
| "RLTrainer._checkpoint": { |
| "total": 0.12118110399933357, |
| "count": 1, |
| "self": 0.12118110399933357 |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
