| { |
| "name": "root", |
| "gauges": { |
| "Pyramids.Policy.Entropy.mean": { |
| "value": 0.43443748354911804, |
| "min": 0.4235185980796814, |
| "max": 1.5154063701629639, |
| "count": 33 |
| }, |
| "Pyramids.Policy.Entropy.sum": { |
| "value": 12901.0556640625, |
| "min": 12664.900390625, |
| "max": 45971.3671875, |
| "count": 33 |
| }, |
| "Pyramids.Step.mean": { |
| "value": 989951.0, |
| "min": 29952.0, |
| "max": 989951.0, |
| "count": 33 |
| }, |
| "Pyramids.Step.sum": { |
| "value": 989951.0, |
| "min": 29952.0, |
| "max": 989951.0, |
| "count": 33 |
| }, |
| "Pyramids.Policy.ExtrinsicValueEstimate.mean": { |
| "value": 0.5546972155570984, |
| "min": -0.1817149817943573, |
| "max": 0.666252076625824, |
| "count": 33 |
| }, |
| "Pyramids.Policy.ExtrinsicValueEstimate.sum": { |
| "value": 156.42462158203125, |
| "min": -43.06645202636719, |
| "max": 187.21682739257812, |
| "count": 33 |
| }, |
| "Pyramids.Policy.RndValueEstimate.mean": { |
| "value": 0.002404846018180251, |
| "min": 0.002404846018180251, |
| "max": 0.16549676656723022, |
| "count": 33 |
| }, |
| "Pyramids.Policy.RndValueEstimate.sum": { |
| "value": 0.6781665682792664, |
| "min": 0.6781665682792664, |
| "max": 39.22273254394531, |
| "count": 33 |
| }, |
| "Pyramids.Losses.PolicyLoss.mean": { |
| "value": 0.06631093798551731, |
| "min": 0.06473006202797463, |
| "max": 0.07458488524378037, |
| "count": 33 |
| }, |
| "Pyramids.Losses.PolicyLoss.sum": { |
| "value": 0.9283531317972423, |
| "min": 0.4891404350577243, |
| "max": 1.0683422551168513, |
| "count": 33 |
| }, |
| "Pyramids.Losses.ValueLoss.mean": { |
| "value": 0.018596447771415114, |
| "min": 0.0004411683731666993, |
| "max": 0.018596447771415114, |
| "count": 33 |
| }, |
| "Pyramids.Losses.ValueLoss.sum": { |
| "value": 0.2603502687998116, |
| "min": 0.00617635722433379, |
| "max": 0.2603502687998116, |
| "count": 33 |
| }, |
| "Pyramids.Policy.LearningRate.mean": { |
| "value": 7.541968914614285e-06, |
| "min": 7.541968914614285e-06, |
| "max": 0.00029515063018788575, |
| "count": 33 |
| }, |
| "Pyramids.Policy.LearningRate.sum": { |
| "value": 0.00010558756480459998, |
| "min": 0.00010558756480459998, |
| "max": 0.0033698476767174993, |
| "count": 33 |
| }, |
| "Pyramids.Policy.Epsilon.mean": { |
| "value": 0.10251395714285716, |
| "min": 0.10251395714285716, |
| "max": 0.19838354285714285, |
| "count": 33 |
| }, |
| "Pyramids.Policy.Epsilon.sum": { |
| "value": 1.4351954000000002, |
| "min": 1.3886848, |
| "max": 2.4851590999999997, |
| "count": 33 |
| }, |
| "Pyramids.Policy.Beta.mean": { |
| "value": 0.0002611443185714286, |
| "min": 0.0002611443185714286, |
| "max": 0.00983851593142857, |
| "count": 33 |
| }, |
| "Pyramids.Policy.Beta.sum": { |
| "value": 0.0036560204600000006, |
| "min": 0.0036560204600000006, |
| "max": 0.11234592175, |
| "count": 33 |
| }, |
| "Pyramids.Losses.RNDLoss.mean": { |
| "value": 0.012335068546235561, |
| "min": 0.012335068546235561, |
| "max": 0.30552953481674194, |
| "count": 33 |
| }, |
| "Pyramids.Losses.RNDLoss.sum": { |
| "value": 0.1726909577846527, |
| "min": 0.1726909577846527, |
| "max": 2.138706684112549, |
| "count": 33 |
| }, |
| "Pyramids.Environment.EpisodeLength.mean": { |
| "value": 308.9901960784314, |
| "min": 277.11764705882354, |
| "max": 999.0, |
| "count": 33 |
| }, |
| "Pyramids.Environment.EpisodeLength.sum": { |
| "value": 31517.0, |
| "min": 15984.0, |
| "max": 32644.0, |
| "count": 33 |
| }, |
| "Pyramids.Environment.CumulativeReward.mean": { |
| "value": 1.5929431232313316, |
| "min": -1.0000000521540642, |
| "max": 1.7032725384422378, |
| "count": 33 |
| }, |
| "Pyramids.Environment.CumulativeReward.sum": { |
| "value": 162.4801985695958, |
| "min": -30.485201686620712, |
| "max": 173.73379892110825, |
| "count": 33 |
| }, |
| "Pyramids.Policy.ExtrinsicReward.mean": { |
| "value": 1.5929431232313316, |
| "min": -1.0000000521540642, |
| "max": 1.7032725384422378, |
| "count": 33 |
| }, |
| "Pyramids.Policy.ExtrinsicReward.sum": { |
| "value": 162.4801985695958, |
| "min": -30.485201686620712, |
| "max": 173.73379892110825, |
| "count": 33 |
| }, |
| "Pyramids.Policy.RndReward.mean": { |
| "value": 0.039537690360043155, |
| "min": 0.037958301095618395, |
| "max": 6.037254820112139, |
| "count": 33 |
| }, |
| "Pyramids.Policy.RndReward.sum": { |
| "value": 4.0328444167244015, |
| "min": 3.871746711753076, |
| "max": 96.59607712179422, |
| "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": "1705886078", |
| "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [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": "2.1.2+cu121", |
| "numpy_version": "1.23.5", |
| "end_time_seconds": "1705888636" |
| }, |
| "total": 2558.08240177, |
| "count": 1, |
| "self": 0.5288137210004606, |
| "children": { |
| "run_training.setup": { |
| "total": 0.05213762199991834, |
| "count": 1, |
| "self": 0.05213762199991834 |
| }, |
| "TrainerController.start_learning": { |
| "total": 2557.501450427, |
| "count": 1, |
| "self": 1.738483751046715, |
| "children": { |
| "TrainerController._reset_env": { |
| "total": 2.3496722790000604, |
| "count": 1, |
| "self": 2.3496722790000604 |
| }, |
| "TrainerController.advance": { |
| "total": 2553.3186067029533, |
| "count": 63905, |
| "self": 1.884540581890633, |
| "children": { |
| "env_step": { |
| "total": 1835.9236210019867, |
| "count": 63905, |
| "self": 1685.1999479329934, |
| "children": { |
| "SubprocessEnvManager._take_step": { |
| "total": 149.64914557998736, |
| "count": 63905, |
| "self": 5.576325240008828, |
| "children": { |
| "TorchPolicy.evaluate": { |
| "total": 144.07282033997853, |
| "count": 62556, |
| "self": 144.07282033997853 |
| } |
| } |
| }, |
| "workers": { |
| "total": 1.074527489005959, |
| "count": 63905, |
| "self": 0.0, |
| "children": { |
| "worker_root": { |
| "total": 2551.1942163599356, |
| "count": 63905, |
| "is_parallel": true, |
| "self": 1009.0133628359422, |
| "children": { |
| "run_training.setup": { |
| "total": 0.0, |
| "count": 0, |
| "is_parallel": true, |
| "self": 0.0, |
| "children": { |
| "steps_from_proto": { |
| "total": 0.0018112220000148227, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.0005384769992815563, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 0.0012727450007332664, |
| "count": 8, |
| "is_parallel": true, |
| "self": 0.0012727450007332664 |
| } |
| } |
| }, |
| "UnityEnvironment.step": { |
| "total": 0.053396148000047106, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.0006709079998472589, |
| "children": { |
| "UnityEnvironment._generate_step_input": { |
| "total": 0.00048075400036395877, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.00048075400036395877 |
| }, |
| "communicator.exchange": { |
| "total": 0.05041723299973455, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.05041723299973455 |
| }, |
| "steps_from_proto": { |
| "total": 0.0018272530001013365, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.00036638300070990226, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 0.0014608699993914342, |
| "count": 8, |
| "is_parallel": true, |
| "self": 0.0014608699993914342 |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "UnityEnvironment.step": { |
| "total": 1542.1808535239934, |
| "count": 63904, |
| "is_parallel": true, |
| "self": 40.7421402619525, |
| "children": { |
| "UnityEnvironment._generate_step_input": { |
| "total": 26.748269288991196, |
| "count": 63904, |
| "is_parallel": true, |
| "self": 26.748269288991196 |
| }, |
| "communicator.exchange": { |
| "total": 1362.401912906936, |
| "count": 63904, |
| "is_parallel": true, |
| "self": 1362.401912906936 |
| }, |
| "steps_from_proto": { |
| "total": 112.28853106611359, |
| "count": 63904, |
| "is_parallel": true, |
| "self": 23.73900141786089, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 88.5495296482527, |
| "count": 511232, |
| "is_parallel": true, |
| "self": 88.5495296482527 |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "trainer_advance": { |
| "total": 715.5104451190759, |
| "count": 63905, |
| "self": 3.4489883240212293, |
| "children": { |
| "process_trajectory": { |
| "total": 142.05216596804985, |
| "count": 63905, |
| "self": 141.84833093404995, |
| "children": { |
| "RLTrainer._checkpoint": { |
| "total": 0.20383503399989422, |
| "count": 2, |
| "self": 0.20383503399989422 |
| } |
| } |
| }, |
| "_update_policy": { |
| "total": 570.0092908270049, |
| "count": 452, |
| "self": 337.0086527660151, |
| "children": { |
| "TorchPPOOptimizer.update": { |
| "total": 233.0006380609898, |
| "count": 22755, |
| "self": 233.0006380609898 |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "trainer_threads": { |
| "total": 1.3310000213095918e-06, |
| "count": 1, |
| "self": 1.3310000213095918e-06 |
| }, |
| "TrainerController._save_models": { |
| "total": 0.09468636299970967, |
| "count": 1, |
| "self": 0.0017423620001864037, |
| "children": { |
| "RLTrainer._checkpoint": { |
| "total": 0.09294400099952327, |
| "count": 1, |
| "self": 0.09294400099952327 |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
