| { |
| "name": "root", |
| "gauges": { |
| "Pyramids.Policy.Entropy.mean": { |
| "value": 0.17490901052951813, |
| "min": 0.16398131847381592, |
| "max": 1.4302674531936646, |
| "count": 100 |
| }, |
| "Pyramids.Policy.Entropy.sum": { |
| "value": 5278.05419921875, |
| "min": 4903.697265625, |
| "max": 43388.59375, |
| "count": 100 |
| }, |
| "Pyramids.Step.mean": { |
| "value": 2999951.0, |
| "min": 29952.0, |
| "max": 2999951.0, |
| "count": 100 |
| }, |
| "Pyramids.Step.sum": { |
| "value": 2999951.0, |
| "min": 29952.0, |
| "max": 2999951.0, |
| "count": 100 |
| }, |
| "Pyramids.Policy.ExtrinsicValueEstimate.mean": { |
| "value": 0.7282366752624512, |
| "min": -0.10632584989070892, |
| "max": 0.8514661192893982, |
| "count": 100 |
| }, |
| "Pyramids.Policy.ExtrinsicValueEstimate.sum": { |
| "value": 211.18862915039062, |
| "min": -25.518203735351562, |
| "max": 258.845703125, |
| "count": 100 |
| }, |
| "Pyramids.Policy.RndValueEstimate.mean": { |
| "value": -0.010904678143560886, |
| "min": -0.019113825634121895, |
| "max": 0.645065426826477, |
| "count": 100 |
| }, |
| "Pyramids.Policy.RndValueEstimate.sum": { |
| "value": -3.1623566150665283, |
| "min": -5.791489124298096, |
| "max": 152.88050842285156, |
| "count": 100 |
| }, |
| "Pyramids.Losses.PolicyLoss.mean": { |
| "value": 0.07045070029562339, |
| "min": 0.06448170247578051, |
| "max": 0.07583584167973723, |
| "count": 100 |
| }, |
| "Pyramids.Losses.PolicyLoss.sum": { |
| "value": 0.9863098041387275, |
| "min": 0.5011433693446519, |
| "max": 1.101917128583106, |
| "count": 100 |
| }, |
| "Pyramids.Losses.ValueLoss.mean": { |
| "value": 0.015463917435789924, |
| "min": 0.00047009329222738805, |
| "max": 0.02875869644473222, |
| "count": 100 |
| }, |
| "Pyramids.Losses.ValueLoss.sum": { |
| "value": 0.21649484410105893, |
| "min": 0.006111212798956045, |
| "max": 0.2539350916665759, |
| "count": 100 |
| }, |
| "Pyramids.Policy.LearningRate.mean": { |
| "value": 1.4725209377642907e-06, |
| "min": 1.4725209377642907e-06, |
| "max": 0.00029838354339596195, |
| "count": 100 |
| }, |
| "Pyramids.Policy.LearningRate.sum": { |
| "value": 2.061529312870007e-05, |
| "min": 2.061529312870007e-05, |
| "max": 0.0038429512190162997, |
| "count": 100 |
| }, |
| "Pyramids.Policy.Epsilon.mean": { |
| "value": 0.10049080714285714, |
| "min": 0.10049080714285714, |
| "max": 0.19946118095238097, |
| "count": 100 |
| }, |
| "Pyramids.Policy.Epsilon.sum": { |
| "value": 1.4068713, |
| "min": 1.3897045333333333, |
| "max": 2.722569266666667, |
| "count": 100 |
| }, |
| "Pyramids.Policy.Beta.mean": { |
| "value": 5.903163357142875e-05, |
| "min": 5.903163357142875e-05, |
| "max": 0.009946171977142856, |
| "count": 100 |
| }, |
| "Pyramids.Policy.Beta.sum": { |
| "value": 0.0008264428700000025, |
| "min": 0.0008264428700000025, |
| "max": 0.12811027163, |
| "count": 100 |
| }, |
| "Pyramids.Losses.RNDLoss.mean": { |
| "value": 0.005767387803643942, |
| "min": 0.00550212012603879, |
| "max": 0.593696653842926, |
| "count": 100 |
| }, |
| "Pyramids.Losses.RNDLoss.sum": { |
| "value": 0.08074343204498291, |
| "min": 0.07702968269586563, |
| "max": 4.155876636505127, |
| "count": 100 |
| }, |
| "Pyramids.Environment.EpisodeLength.mean": { |
| "value": 236.5984251968504, |
| "min": 217.13533834586465, |
| "max": 999.0, |
| "count": 100 |
| }, |
| "Pyramids.Environment.EpisodeLength.sum": { |
| "value": 30048.0, |
| "min": 15984.0, |
| "max": 32849.0, |
| "count": 100 |
| }, |
| "Pyramids.Environment.CumulativeReward.mean": { |
| "value": 1.7476456504989797, |
| "min": -1.0000000521540642, |
| "max": 1.7744094390334106, |
| "count": 100 |
| }, |
| "Pyramids.Environment.CumulativeReward.sum": { |
| "value": 221.95099761337042, |
| "min": -32.000001668930054, |
| "max": 241.5609978362918, |
| "count": 100 |
| }, |
| "Pyramids.Policy.ExtrinsicReward.mean": { |
| "value": 1.7476456504989797, |
| "min": -1.0000000521540642, |
| "max": 1.7744094390334106, |
| "count": 100 |
| }, |
| "Pyramids.Policy.ExtrinsicReward.sum": { |
| "value": 221.95099761337042, |
| "min": -32.000001668930054, |
| "max": 241.5609978362918, |
| "count": 100 |
| }, |
| "Pyramids.Policy.RndReward.mean": { |
| "value": 0.014373364153592645, |
| "min": 0.0126526198067389, |
| "max": 14.521467708051205, |
| "count": 100 |
| }, |
| "Pyramids.Policy.RndReward.sum": { |
| "value": 1.825417247506266, |
| "min": 1.6723010244968464, |
| "max": 232.34348332881927, |
| "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": "1682587399", |
| "python_version": "3.9.16 (main, Mar 8 2023, 14:00:05) \n[GCC 11.2.0]", |
| "command_line_arguments": "/home/ntrant/anaconda3/envs/rl/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+cu113", |
| "numpy_version": "1.21.2", |
| "end_time_seconds": "1682589781" |
| }, |
| "total": 2382.4878098119516, |
| "count": 1, |
| "self": 0.21826302981935441, |
| "children": { |
| "run_training.setup": { |
| "total": 0.01288121403194964, |
| "count": 1, |
| "self": 0.01288121403194964 |
| }, |
| "TrainerController.start_learning": { |
| "total": 2382.2566655681003, |
| "count": 1, |
| "self": 1.9276359151117504, |
| "children": { |
| "TrainerController._reset_env": { |
| "total": 3.888193927006796, |
| "count": 1, |
| "self": 3.888193927006796 |
| }, |
| "TrainerController.advance": { |
| "total": 2376.393455961952, |
| "count": 194535, |
| "self": 1.8915775606874377, |
| "children": { |
| "env_step": { |
| "total": 1443.0404986417852, |
| "count": 194535, |
| "self": 1283.5638633763883, |
| "children": { |
| "SubprocessEnvManager._take_step": { |
| "total": 158.27946001267992, |
| "count": 194535, |
| "self": 6.123884355183691, |
| "children": { |
| "TorchPolicy.evaluate": { |
| "total": 152.15557565749623, |
| "count": 187557, |
| "self": 152.15557565749623 |
| } |
| } |
| }, |
| "workers": { |
| "total": 1.1971752527169883, |
| "count": 194535, |
| "self": 0.0, |
| "children": { |
| "worker_root": { |
| "total": 2379.4368221322075, |
| "count": 194535, |
| "is_parallel": true, |
| "self": 1226.9768003886566, |
| "children": { |
| "run_training.setup": { |
| "total": 0.0, |
| "count": 0, |
| "is_parallel": true, |
| "self": 0.0, |
| "children": { |
| "steps_from_proto": { |
| "total": 0.0009483250323683023, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.0002904192078858614, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 0.000657905824482441, |
| "count": 8, |
| "is_parallel": true, |
| "self": 0.000657905824482441 |
| } |
| } |
| }, |
| "UnityEnvironment.step": { |
| "total": 0.02145201014354825, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.00024907919578254223, |
| "children": { |
| "UnityEnvironment._generate_step_input": { |
| "total": 0.00029695802368223667, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.00029695802368223667 |
| }, |
| "communicator.exchange": { |
| "total": 0.020106848096475005, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.020106848096475005 |
| }, |
| "steps_from_proto": { |
| "total": 0.0007991248276084661, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.00018501910381019115, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 0.000614105723798275, |
| "count": 8, |
| "is_parallel": true, |
| "self": 0.000614105723798275 |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "UnityEnvironment.step": { |
| "total": 1152.460021743551, |
| "count": 194534, |
| "is_parallel": true, |
| "self": 37.468936015153304, |
| "children": { |
| "UnityEnvironment._generate_step_input": { |
| "total": 25.305287588387728, |
| "count": 194534, |
| "is_parallel": true, |
| "self": 25.305287588387728 |
| }, |
| "communicator.exchange": { |
| "total": 981.8986218154896, |
| "count": 194534, |
| "is_parallel": true, |
| "self": 981.8986218154896 |
| }, |
| "steps_from_proto": { |
| "total": 107.78717632452026, |
| "count": 194534, |
| "is_parallel": true, |
| "self": 23.479633159702644, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 84.30754316481762, |
| "count": 1556272, |
| "is_parallel": true, |
| "self": 84.30754316481762 |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "trainer_advance": { |
| "total": 931.4613797594793, |
| "count": 194535, |
| "self": 3.435052201617509, |
| "children": { |
| "process_trajectory": { |
| "total": 156.43625362799503, |
| "count": 194535, |
| "self": 156.13586911163293, |
| "children": { |
| "RLTrainer._checkpoint": { |
| "total": 0.30038451636210084, |
| "count": 6, |
| "self": 0.30038451636210084 |
| } |
| } |
| }, |
| "_update_policy": { |
| "total": 771.5900739298668, |
| "count": 1390, |
| "self": 467.68752431566827, |
| "children": { |
| "TorchPPOOptimizer.update": { |
| "total": 303.9025496141985, |
| "count": 68376, |
| "self": 303.9025496141985 |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "trainer_threads": { |
| "total": 6.400514394044876e-07, |
| "count": 1, |
| "self": 6.400514394044876e-07 |
| }, |
| "TrainerController._save_models": { |
| "total": 0.047379123978316784, |
| "count": 1, |
| "self": 0.0005925619043409824, |
| "children": { |
| "RLTrainer._checkpoint": { |
| "total": 0.0467865620739758, |
| "count": 1, |
| "self": 0.0467865620739758 |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
