| { |
| "name": "root", |
| "gauges": { |
| "Pyramids.Policy.Entropy.mean": { |
| "value": 0.5026072859764099, |
| "min": 0.5026072859764099, |
| "max": 1.4436146020889282, |
| "count": 33 |
| }, |
| "Pyramids.Policy.Entropy.sum": { |
| "value": 15110.3857421875, |
| "min": 15110.3857421875, |
| "max": 43793.4921875, |
| "count": 33 |
| }, |
| "Pyramids.Step.mean": { |
| "value": 989927.0, |
| "min": 29942.0, |
| "max": 989927.0, |
| "count": 33 |
| }, |
| "Pyramids.Step.sum": { |
| "value": 989927.0, |
| "min": 29942.0, |
| "max": 989927.0, |
| "count": 33 |
| }, |
| "Pyramids.Policy.ExtrinsicValueEstimate.mean": { |
| "value": 0.4582596719264984, |
| "min": -0.10647869855165482, |
| "max": 0.46304410696029663, |
| "count": 33 |
| }, |
| "Pyramids.Policy.ExtrinsicValueEstimate.sum": { |
| "value": 124.18836975097656, |
| "min": -25.554887771606445, |
| "max": 124.55886840820312, |
| "count": 33 |
| }, |
| "Pyramids.Policy.RndValueEstimate.mean": { |
| "value": 0.01799023523926735, |
| "min": -0.03115887939929962, |
| "max": 0.5443099141120911, |
| "count": 33 |
| }, |
| "Pyramids.Policy.RndValueEstimate.sum": { |
| "value": 4.875353813171387, |
| "min": -8.381738662719727, |
| "max": 129.00144958496094, |
| "count": 33 |
| }, |
| "Pyramids.Losses.PolicyLoss.mean": { |
| "value": 0.07030688133852979, |
| "min": 0.06439152579353986, |
| "max": 0.07281681260649171, |
| "count": 33 |
| }, |
| "Pyramids.Losses.PolicyLoss.sum": { |
| "value": 0.984296338739417, |
| "min": 0.509717688245442, |
| "max": 1.0233207552761694, |
| "count": 33 |
| }, |
| "Pyramids.Losses.ValueLoss.mean": { |
| "value": 0.016910908521995657, |
| "min": 3.6694227394499604e-05, |
| "max": 0.016910908521995657, |
| "count": 33 |
| }, |
| "Pyramids.Losses.ValueLoss.sum": { |
| "value": 0.2367527193079392, |
| "min": 0.0005137191835229945, |
| "max": 0.25074333061125154, |
| "count": 33 |
| }, |
| "Pyramids.Policy.LearningRate.mean": { |
| "value": 7.322304702121432e-06, |
| "min": 7.322304702121432e-06, |
| "max": 0.0002952333444460286, |
| "count": 33 |
| }, |
| "Pyramids.Policy.LearningRate.sum": { |
| "value": 0.00010251226582970005, |
| "min": 0.00010251226582970005, |
| "max": 0.0035091131302956995, |
| "count": 33 |
| }, |
| "Pyramids.Policy.Epsilon.mean": { |
| "value": 0.10244073571428569, |
| "min": 0.10244073571428569, |
| "max": 0.19841111428571429, |
| "count": 33 |
| }, |
| "Pyramids.Policy.Epsilon.sum": { |
| "value": 1.4341702999999997, |
| "min": 1.3888778, |
| "max": 2.5697043000000006, |
| "count": 33 |
| }, |
| "Pyramids.Policy.Beta.mean": { |
| "value": 0.00025382949785714295, |
| "min": 0.00025382949785714295, |
| "max": 0.009841270317142856, |
| "count": 33 |
| }, |
| "Pyramids.Policy.Beta.sum": { |
| "value": 0.003553612970000001, |
| "min": 0.003553612970000001, |
| "max": 0.11699345957, |
| "count": 33 |
| }, |
| "Pyramids.Losses.RNDLoss.mean": { |
| "value": 0.012287263758480549, |
| "min": 0.011541834101080894, |
| "max": 0.5963875651359558, |
| "count": 33 |
| }, |
| "Pyramids.Losses.RNDLoss.sum": { |
| "value": 0.17202168703079224, |
| "min": 0.16158567368984222, |
| "max": 4.174713134765625, |
| "count": 33 |
| }, |
| "Pyramids.Environment.EpisodeLength.mean": { |
| "value": 378.7901234567901, |
| "min": 378.7901234567901, |
| "max": 999.0, |
| "count": 33 |
| }, |
| "Pyramids.Environment.EpisodeLength.sum": { |
| "value": 30682.0, |
| "min": 16613.0, |
| "max": 33111.0, |
| "count": 33 |
| }, |
| "Pyramids.Environment.CumulativeReward.mean": { |
| "value": 1.5470987463622918, |
| "min": -0.999987552408129, |
| "max": 1.5470987463622918, |
| "count": 33 |
| }, |
| "Pyramids.Environment.CumulativeReward.sum": { |
| "value": 125.31499845534563, |
| "min": -31.999601677060127, |
| "max": 125.31499845534563, |
| "count": 33 |
| }, |
| "Pyramids.Policy.ExtrinsicReward.mean": { |
| "value": 1.5470987463622918, |
| "min": -0.999987552408129, |
| "max": 1.5470987463622918, |
| "count": 33 |
| }, |
| "Pyramids.Policy.ExtrinsicReward.sum": { |
| "value": 125.31499845534563, |
| "min": -31.999601677060127, |
| "max": 125.31499845534563, |
| "count": 33 |
| }, |
| "Pyramids.Policy.RndReward.mean": { |
| "value": 0.04873414869193149, |
| "min": 0.04873414869193149, |
| "max": 12.113140689099536, |
| "count": 33 |
| }, |
| "Pyramids.Policy.RndReward.sum": { |
| "value": 3.9474660440464504, |
| "min": 3.529839080001693, |
| "max": 205.92339171469212, |
| "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": "1777799116", |
| "python_version": "3.10.12 | packaged by conda-forge | (main, Jun 23 2023, 22:40:32) [GCC 12.3.0]", |
| "command_line_arguments": "/home/user/miniforge3/envs/py31012/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --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": "1777800086" |
| }, |
| "total": 970.7906739129976, |
| "count": 1, |
| "self": 0.31871445900105755, |
| "children": { |
| "run_training.setup": { |
| "total": 0.013402051998127718, |
| "count": 1, |
| "self": 0.013402051998127718 |
| }, |
| "TrainerController.start_learning": { |
| "total": 970.4585574019984, |
| "count": 1, |
| "self": 1.1806836719842977, |
| "children": { |
| "TrainerController._reset_env": { |
| "total": 1.4449513839972496, |
| "count": 1, |
| "self": 1.4449513839972496 |
| }, |
| "TrainerController.advance": { |
| "total": 967.8050073450177, |
| "count": 63584, |
| "self": 1.2481639090037788, |
| "children": { |
| "env_step": { |
| "total": 603.1725988958715, |
| "count": 63584, |
| "self": 540.4988386426339, |
| "children": { |
| "SubprocessEnvManager._take_step": { |
| "total": 61.8649808001137, |
| "count": 63584, |
| "self": 2.765883009200479, |
| "children": { |
| "TorchPolicy.evaluate": { |
| "total": 59.09909779091322, |
| "count": 62561, |
| "self": 59.09909779091322 |
| } |
| } |
| }, |
| "workers": { |
| "total": 0.8087794531238615, |
| "count": 63584, |
| "self": 0.0, |
| "children": { |
| "worker_root": { |
| "total": 968.9295175952648, |
| "count": 63584, |
| "is_parallel": true, |
| "self": 493.7550299362083, |
| "children": { |
| "run_training.setup": { |
| "total": 0.0, |
| "count": 0, |
| "is_parallel": true, |
| "self": 0.0, |
| "children": { |
| "steps_from_proto": { |
| "total": 0.0010336509985791054, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.00033265700039919466, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 0.0007009939981799107, |
| "count": 8, |
| "is_parallel": true, |
| "self": 0.0007009939981799107 |
| } |
| } |
| }, |
| "UnityEnvironment.step": { |
| "total": 0.027043032001529355, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.0002582729975983966, |
| "children": { |
| "UnityEnvironment._generate_step_input": { |
| "total": 0.00022782300220569596, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.00022782300220569596 |
| }, |
| "communicator.exchange": { |
| "total": 0.025780371001019375, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.025780371001019375 |
| }, |
| "steps_from_proto": { |
| "total": 0.0007765650007058866, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.00019709200205397792, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 0.0005794729986519087, |
| "count": 8, |
| "is_parallel": true, |
| "self": 0.0005794729986519087 |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "UnityEnvironment.step": { |
| "total": 475.17448765905647, |
| "count": 63583, |
| "is_parallel": true, |
| "self": 15.020436929426069, |
| "children": { |
| "UnityEnvironment._generate_step_input": { |
| "total": 10.360689733675827, |
| "count": 63583, |
| "is_parallel": true, |
| "self": 10.360689733675827 |
| }, |
| "communicator.exchange": { |
| "total": 407.7471936863258, |
| "count": 63583, |
| "is_parallel": true, |
| "self": 407.7471936863258 |
| }, |
| "steps_from_proto": { |
| "total": 42.0461673096288, |
| "count": 63583, |
| "is_parallel": true, |
| "self": 10.174381445202016, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 31.871785864426784, |
| "count": 508664, |
| "is_parallel": true, |
| "self": 31.871785864426784 |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "trainer_advance": { |
| "total": 363.3842445401424, |
| "count": 63584, |
| "self": 2.3287487244961085, |
| "children": { |
| "process_trajectory": { |
| "total": 68.82358752960499, |
| "count": 63584, |
| "self": 68.75443767860634, |
| "children": { |
| "RLTrainer._checkpoint": { |
| "total": 0.06914985099865589, |
| "count": 2, |
| "self": 0.06914985099865589 |
| } |
| } |
| }, |
| "_update_policy": { |
| "total": 292.2319082860413, |
| "count": 454, |
| "self": 149.69308987889235, |
| "children": { |
| "TorchPPOOptimizer.update": { |
| "total": 142.53881840714894, |
| "count": 22803, |
| "self": 142.53881840714894 |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "trainer_threads": { |
| "total": 9.779978427104652e-07, |
| "count": 1, |
| "self": 9.779978427104652e-07 |
| }, |
| "TrainerController._save_models": { |
| "total": 0.027914023001358146, |
| "count": 1, |
| "self": 0.0005242289989837445, |
| "children": { |
| "RLTrainer._checkpoint": { |
| "total": 0.0273897940023744, |
| "count": 1, |
| "self": 0.0273897940023744 |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
