| { |
| "name": "root", |
| "gauges": { |
| "Pyramids.Policy.Entropy.mean": { |
| "value": 0.2911440432071686, |
| "min": 0.2911440432071686, |
| "max": 1.462047815322876, |
| "count": 33 |
| }, |
| "Pyramids.Policy.Entropy.sum": { |
| "value": 8664.4462890625, |
| "min": 8664.4462890625, |
| "max": 44352.68359375, |
| "count": 33 |
| }, |
| "Pyramids.Step.mean": { |
| "value": 989995.0, |
| "min": 29980.0, |
| "max": 989995.0, |
| "count": 33 |
| }, |
| "Pyramids.Step.sum": { |
| "value": 989995.0, |
| "min": 29980.0, |
| "max": 989995.0, |
| "count": 33 |
| }, |
| "Pyramids.Policy.ExtrinsicValueEstimate.mean": { |
| "value": 0.47615519165992737, |
| "min": -0.11998161673545837, |
| "max": 0.5694788694381714, |
| "count": 33 |
| }, |
| "Pyramids.Policy.ExtrinsicValueEstimate.sum": { |
| "value": 126.1811294555664, |
| "min": -28.67560577392578, |
| "max": 156.606689453125, |
| "count": 33 |
| }, |
| "Pyramids.Policy.RndValueEstimate.mean": { |
| "value": 0.0297621488571167, |
| "min": -0.008069469593465328, |
| "max": 0.38934046030044556, |
| "count": 33 |
| }, |
| "Pyramids.Policy.RndValueEstimate.sum": { |
| "value": 7.886969566345215, |
| "min": -2.186826229095459, |
| "max": 93.0523681640625, |
| "count": 33 |
| }, |
| "Pyramids.Losses.PolicyLoss.mean": { |
| "value": 0.06767994894964158, |
| "min": 0.06550985406458128, |
| "max": 0.07343427056820337, |
| "count": 33 |
| }, |
| "Pyramids.Losses.PolicyLoss.sum": { |
| "value": 1.0151992342446237, |
| "min": 0.587474164545627, |
| "max": 1.0652697917436906, |
| "count": 33 |
| }, |
| "Pyramids.Losses.ValueLoss.mean": { |
| "value": 0.01517806023656424, |
| "min": 0.0014229360843799252, |
| "max": 0.01675326295562805, |
| "count": 33 |
| }, |
| "Pyramids.Losses.ValueLoss.sum": { |
| "value": 0.22767090354846362, |
| "min": 0.019921105181318954, |
| "max": 0.2447463477049799, |
| "count": 33 |
| }, |
| "Pyramids.Policy.LearningRate.mean": { |
| "value": 7.476357507913331e-06, |
| "min": 7.476357507913331e-06, |
| "max": 0.00029476455174515, |
| "count": 33 |
| }, |
| "Pyramids.Policy.LearningRate.sum": { |
| "value": 0.00011214536261869996, |
| "min": 0.00011214536261869996, |
| "max": 0.0037599853466716, |
| "count": 33 |
| }, |
| "Pyramids.Policy.Epsilon.mean": { |
| "value": 0.10249208666666668, |
| "min": 0.10249208666666668, |
| "max": 0.19825484999999998, |
| "count": 33 |
| }, |
| "Pyramids.Policy.Epsilon.sum": { |
| "value": 1.5373813, |
| "min": 1.4778100000000003, |
| "max": 2.6533284000000004, |
| "count": 33 |
| }, |
| "Pyramids.Policy.Beta.mean": { |
| "value": 0.000258959458, |
| "min": 0.000258959458, |
| "max": 0.009825659514999998, |
| "count": 33 |
| }, |
| "Pyramids.Policy.Beta.sum": { |
| "value": 0.0038843918700000005, |
| "min": 0.0038843918700000005, |
| "max": 0.12534750715999998, |
| "count": 33 |
| }, |
| "Pyramids.Losses.RNDLoss.mean": { |
| "value": 0.013900975696742535, |
| "min": 0.013893802650272846, |
| "max": 0.369596004486084, |
| "count": 33 |
| }, |
| "Pyramids.Losses.RNDLoss.sum": { |
| "value": 0.20851463079452515, |
| "min": 0.1945132315158844, |
| "max": 2.956768035888672, |
| "count": 33 |
| }, |
| "Pyramids.Environment.EpisodeLength.mean": { |
| "value": 378.8051948051948, |
| "min": 337.0769230769231, |
| "max": 979.5757575757576, |
| "count": 33 |
| }, |
| "Pyramids.Environment.EpisodeLength.sum": { |
| "value": 29168.0, |
| "min": 18952.0, |
| "max": 32975.0, |
| "count": 33 |
| }, |
| "Pyramids.Environment.CumulativeReward.mean": { |
| "value": 1.5172778975653958, |
| "min": -0.8546250502113253, |
| "max": 1.55523476101782, |
| "count": 33 |
| }, |
| "Pyramids.Environment.CumulativeReward.sum": { |
| "value": 116.83039811253548, |
| "min": -27.34800160676241, |
| "max": 143.08159801363945, |
| "count": 33 |
| }, |
| "Pyramids.Policy.ExtrinsicReward.mean": { |
| "value": 1.5172778975653958, |
| "min": -0.8546250502113253, |
| "max": 1.55523476101782, |
| "count": 33 |
| }, |
| "Pyramids.Policy.ExtrinsicReward.sum": { |
| "value": 116.83039811253548, |
| "min": -27.34800160676241, |
| "max": 143.08159801363945, |
| "count": 33 |
| }, |
| "Pyramids.Policy.RndReward.mean": { |
| "value": 0.055269279538399795, |
| "min": 0.05243994093034417, |
| "max": 5.521331264823675, |
| "count": 33 |
| }, |
| "Pyramids.Policy.RndReward.sum": { |
| "value": 4.255734524456784, |
| "min": 3.9329955697758123, |
| "max": 110.4266252964735, |
| "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": "1767580876", |
| "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=PyramidsTraining --no-graphics", |
| "mlagents_version": "1.2.0.dev0", |
| "mlagents_envs_version": "1.2.0.dev0", |
| "communication_protocol_version": "1.5.0", |
| "pytorch_version": "2.8.0+cu128", |
| "numpy_version": "1.23.5", |
| "end_time_seconds": "1767583041" |
| }, |
| "total": 2164.975924568, |
| "count": 1, |
| "self": 0.4806688070002565, |
| "children": { |
| "run_training.setup": { |
| "total": 0.023272053000255255, |
| "count": 1, |
| "self": 0.023272053000255255 |
| }, |
| "TrainerController.start_learning": { |
| "total": 2164.4719837079997, |
| "count": 1, |
| "self": 1.2367837740043797, |
| "children": { |
| "TrainerController._reset_env": { |
| "total": 2.0503934470002605, |
| "count": 1, |
| "self": 2.0503934470002605 |
| }, |
| "TrainerController.advance": { |
| "total": 2161.110011202995, |
| "count": 64096, |
| "self": 1.2565605120639702, |
| "children": { |
| "env_step": { |
| "total": 1534.988698559905, |
| "count": 64096, |
| "self": 1394.3631182469794, |
| "children": { |
| "SubprocessEnvManager._take_step": { |
| "total": 139.88459632396507, |
| "count": 64096, |
| "self": 4.405007860925252, |
| "children": { |
| "TorchPolicy.evaluate": { |
| "total": 135.47958846303982, |
| "count": 62561, |
| "self": 135.47958846303982 |
| } |
| } |
| }, |
| "workers": { |
| "total": 0.7409839889605792, |
| "count": 64096, |
| "self": 0.0, |
| "children": { |
| "worker_root": { |
| "total": 2157.77113635498, |
| "count": 64096, |
| "is_parallel": true, |
| "self": 875.1152142279088, |
| "children": { |
| "run_training.setup": { |
| "total": 0.0, |
| "count": 0, |
| "is_parallel": true, |
| "self": 0.0, |
| "children": { |
| "steps_from_proto": { |
| "total": 0.0020046910003657104, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.000684017000367021, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 0.0013206739999986894, |
| "count": 8, |
| "is_parallel": true, |
| "self": 0.0013206739999986894 |
| } |
| } |
| }, |
| "UnityEnvironment.step": { |
| "total": 0.05232849399999395, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.0005599740002253384, |
| "children": { |
| "UnityEnvironment._generate_step_input": { |
| "total": 0.00046264699994935654, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.00046264699994935654 |
| }, |
| "communicator.exchange": { |
| "total": 0.049591359999794804, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.049591359999794804 |
| }, |
| "steps_from_proto": { |
| "total": 0.0017145130000244535, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.0003568800002540229, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 0.0013576329997704306, |
| "count": 8, |
| "is_parallel": true, |
| "self": 0.0013576329997704306 |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "UnityEnvironment.step": { |
| "total": 1282.6559221270713, |
| "count": 64095, |
| "is_parallel": true, |
| "self": 33.263558359869876, |
| "children": { |
| "UnityEnvironment._generate_step_input": { |
| "total": 22.565035537101267, |
| "count": 64095, |
| "is_parallel": true, |
| "self": 22.565035537101267 |
| }, |
| "communicator.exchange": { |
| "total": 1122.9390805010898, |
| "count": 64095, |
| "is_parallel": true, |
| "self": 1122.9390805010898 |
| }, |
| "steps_from_proto": { |
| "total": 103.88824772901035, |
| "count": 64095, |
| "is_parallel": true, |
| "self": 21.70233003673411, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 82.18591769227623, |
| "count": 512760, |
| "is_parallel": true, |
| "self": 82.18591769227623 |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "trainer_advance": { |
| "total": 624.8647521310259, |
| "count": 64096, |
| "self": 2.5649058131380116, |
| "children": { |
| "process_trajectory": { |
| "total": 121.34610773987924, |
| "count": 64096, |
| "self": 121.17289571287938, |
| "children": { |
| "RLTrainer._checkpoint": { |
| "total": 0.17321202699986316, |
| "count": 2, |
| "self": 0.17321202699986316 |
| } |
| } |
| }, |
| "_update_policy": { |
| "total": 500.9537385780086, |
| "count": 462, |
| "self": 277.82036602109974, |
| "children": { |
| "TorchPPOOptimizer.update": { |
| "total": 223.13337255690885, |
| "count": 22716, |
| "self": 223.13337255690885 |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "trainer_threads": { |
| "total": 1.174999852082692e-06, |
| "count": 1, |
| "self": 1.174999852082692e-06 |
| }, |
| "TrainerController._save_models": { |
| "total": 0.07479410900032235, |
| "count": 1, |
| "self": 0.0009782160004760954, |
| "children": { |
| "RLTrainer._checkpoint": { |
| "total": 0.07381589299984626, |
| "count": 1, |
| "self": 0.07381589299984626 |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
