| { |
| "name": "root", |
| "gauges": { |
| "Pyramids.Policy.Entropy.mean": { |
| "value": 0.39236167073249817, |
| "min": 0.39236167073249817, |
| "max": 1.4935498237609863, |
| "count": 33 |
| }, |
| "Pyramids.Policy.Entropy.sum": { |
| "value": 11695.5166015625, |
| "min": 11695.5166015625, |
| "max": 45308.328125, |
| "count": 33 |
| }, |
| "Pyramids.Step.mean": { |
| "value": 989930.0, |
| "min": 29962.0, |
| "max": 989930.0, |
| "count": 33 |
| }, |
| "Pyramids.Step.sum": { |
| "value": 989930.0, |
| "min": 29962.0, |
| "max": 989930.0, |
| "count": 33 |
| }, |
| "Pyramids.Policy.ExtrinsicValueEstimate.mean": { |
| "value": 0.5337557792663574, |
| "min": -0.1348305344581604, |
| "max": 0.5596157312393188, |
| "count": 33 |
| }, |
| "Pyramids.Policy.ExtrinsicValueEstimate.sum": { |
| "value": 147.31658935546875, |
| "min": -32.08966827392578, |
| "max": 153.334716796875, |
| "count": 33 |
| }, |
| "Pyramids.Policy.RndValueEstimate.mean": { |
| "value": -0.16169095039367676, |
| "min": -0.34805065393447876, |
| "max": 0.15681646764278412, |
| "count": 33 |
| }, |
| "Pyramids.Policy.RndValueEstimate.sum": { |
| "value": -44.62670135498047, |
| "min": -95.36587524414062, |
| "max": 37.79277038574219, |
| "count": 33 |
| }, |
| "Pyramids.Losses.PolicyLoss.mean": { |
| "value": 0.06811334140537142, |
| "min": 0.06547812474032287, |
| "max": 0.07323475245558281, |
| "count": 33 |
| }, |
| "Pyramids.Losses.PolicyLoss.sum": { |
| "value": 0.9535867796751999, |
| "min": 0.49047698236964427, |
| "max": 1.0752853873532775, |
| "count": 33 |
| }, |
| "Pyramids.Losses.ValueLoss.mean": { |
| "value": 0.0180244758147655, |
| "min": 0.001364037501759713, |
| "max": 0.022849702598510442, |
| "count": 33 |
| }, |
| "Pyramids.Losses.ValueLoss.sum": { |
| "value": 0.252342661406717, |
| "min": 0.017732487522876268, |
| "max": 0.3198958363791462, |
| "count": 33 |
| }, |
| "Pyramids.Policy.LearningRate.mean": { |
| "value": 7.59164032662857e-06, |
| "min": 7.59164032662857e-06, |
| "max": 0.00029523797301591427, |
| "count": 33 |
| }, |
| "Pyramids.Policy.LearningRate.sum": { |
| "value": 0.00010628296457279998, |
| "min": 0.00010628296457279998, |
| "max": 0.0036092112969295996, |
| "count": 33 |
| }, |
| "Pyramids.Policy.Epsilon.mean": { |
| "value": 0.10253051428571429, |
| "min": 0.10253051428571429, |
| "max": 0.19841265714285714, |
| "count": 33 |
| }, |
| "Pyramids.Policy.Epsilon.sum": { |
| "value": 1.4354272000000001, |
| "min": 1.3888886, |
| "max": 2.5275016999999997, |
| "count": 33 |
| }, |
| "Pyramids.Policy.Beta.mean": { |
| "value": 0.0002627983771428571, |
| "min": 0.0002627983771428571, |
| "max": 0.009841424448571428, |
| "count": 33 |
| }, |
| "Pyramids.Policy.Beta.sum": { |
| "value": 0.00367917728, |
| "min": 0.00367917728, |
| "max": 0.12031673295999999, |
| "count": 33 |
| }, |
| "Pyramids.Losses.RNDLoss.mean": { |
| "value": 0.011338028125464916, |
| "min": 0.011338028125464916, |
| "max": 0.33617809414863586, |
| "count": 33 |
| }, |
| "Pyramids.Losses.RNDLoss.sum": { |
| "value": 0.15873239934444427, |
| "min": 0.15873239934444427, |
| "max": 2.3532466888427734, |
| "count": 33 |
| }, |
| "Pyramids.Environment.EpisodeLength.mean": { |
| "value": 358.76190476190476, |
| "min": 331.35632183908046, |
| "max": 986.5, |
| "count": 33 |
| }, |
| "Pyramids.Environment.EpisodeLength.sum": { |
| "value": 30136.0, |
| "min": 16505.0, |
| "max": 33810.0, |
| "count": 33 |
| }, |
| "Pyramids.Environment.CumulativeReward.mean": { |
| "value": 1.56979046034671, |
| "min": -0.9254242947155779, |
| "max": 1.5996574555662857, |
| "count": 33 |
| }, |
| "Pyramids.Environment.CumulativeReward.sum": { |
| "value": 131.86239866912365, |
| "min": -30.53900172561407, |
| "max": 139.17019863426685, |
| "count": 33 |
| }, |
| "Pyramids.Policy.ExtrinsicReward.mean": { |
| "value": 1.56979046034671, |
| "min": -0.9254242947155779, |
| "max": 1.5996574555662857, |
| "count": 33 |
| }, |
| "Pyramids.Policy.ExtrinsicReward.sum": { |
| "value": 131.86239866912365, |
| "min": -30.53900172561407, |
| "max": 139.17019863426685, |
| "count": 33 |
| }, |
| "Pyramids.Policy.RndReward.mean": { |
| "value": 0.04215670825786739, |
| "min": 0.03957248334813028, |
| "max": 6.225102385725169, |
| "count": 33 |
| }, |
| "Pyramids.Policy.RndReward.sum": { |
| "value": 3.5411634936608607, |
| "min": 3.4428060512873344, |
| "max": 105.82674055732787, |
| "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": "1736929808", |
| "python_version": "3.10.12 (main, Nov 6 2024, 20:22:13) [GCC 11.4.0]", |
| "command_line_arguments": "/usr/local/bin/mlagents-learn ./ml-agents/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": "2.5.1+cu121", |
| "numpy_version": "1.23.5", |
| "end_time_seconds": "1736931975" |
| }, |
| "total": 2166.829852895, |
| "count": 1, |
| "self": 0.4770183579994409, |
| "children": { |
| "run_training.setup": { |
| "total": 0.1072793040000306, |
| "count": 1, |
| "self": 0.1072793040000306 |
| }, |
| "TrainerController.start_learning": { |
| "total": 2166.2455552330002, |
| "count": 1, |
| "self": 1.3652455579749585, |
| "children": { |
| "TrainerController._reset_env": { |
| "total": 5.967830224000011, |
| "count": 1, |
| "self": 5.967830224000011 |
| }, |
| "TrainerController.advance": { |
| "total": 2158.8289077870254, |
| "count": 63733, |
| "self": 1.4177732519669917, |
| "children": { |
| "env_step": { |
| "total": 1465.8169747520426, |
| "count": 63733, |
| "self": 1317.0770374770862, |
| "children": { |
| "SubprocessEnvManager._take_step": { |
| "total": 147.94438495099206, |
| "count": 63733, |
| "self": 4.504026178036952, |
| "children": { |
| "TorchPolicy.evaluate": { |
| "total": 143.4403587729551, |
| "count": 62568, |
| "self": 143.4403587729551 |
| } |
| } |
| }, |
| "workers": { |
| "total": 0.7955523239643867, |
| "count": 63733, |
| "self": 0.0, |
| "children": { |
| "worker_root": { |
| "total": 2161.564255165001, |
| "count": 63733, |
| "is_parallel": true, |
| "self": 956.3367556089802, |
| "children": { |
| "run_training.setup": { |
| "total": 0.0, |
| "count": 0, |
| "is_parallel": true, |
| "self": 0.0, |
| "children": { |
| "steps_from_proto": { |
| "total": 0.0025466420000270773, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.0006635730001107731, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 0.0018830689999163042, |
| "count": 8, |
| "is_parallel": true, |
| "self": 0.0018830689999163042 |
| } |
| } |
| }, |
| "UnityEnvironment.step": { |
| "total": 0.04606066600001668, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.0006850230000168267, |
| "children": { |
| "UnityEnvironment._generate_step_input": { |
| "total": 0.0005034249999766871, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.0005034249999766871 |
| }, |
| "communicator.exchange": { |
| "total": 0.04327532600001405, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.04327532600001405 |
| }, |
| "steps_from_proto": { |
| "total": 0.0015968920000091202, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.0003393630000232406, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 0.0012575289999858796, |
| "count": 8, |
| "is_parallel": true, |
| "self": 0.0012575289999858796 |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "UnityEnvironment.step": { |
| "total": 1205.227499556021, |
| "count": 63732, |
| "is_parallel": true, |
| "self": 33.01331578095824, |
| "children": { |
| "UnityEnvironment._generate_step_input": { |
| "total": 22.616775073012946, |
| "count": 63732, |
| "is_parallel": true, |
| "self": 22.616775073012946 |
| }, |
| "communicator.exchange": { |
| "total": 1056.1542160870326, |
| "count": 63732, |
| "is_parallel": true, |
| "self": 1056.1542160870326 |
| }, |
| "steps_from_proto": { |
| "total": 93.44319261501721, |
| "count": 63732, |
| "is_parallel": true, |
| "self": 18.755360305883414, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 74.6878323091338, |
| "count": 509856, |
| "is_parallel": true, |
| "self": 74.6878323091338 |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "trainer_advance": { |
| "total": 691.5941597830157, |
| "count": 63733, |
| "self": 2.6953704130118012, |
| "children": { |
| "process_trajectory": { |
| "total": 131.04879736200223, |
| "count": 63733, |
| "self": 130.79655361400205, |
| "children": { |
| "RLTrainer._checkpoint": { |
| "total": 0.2522437480001827, |
| "count": 2, |
| "self": 0.2522437480001827 |
| } |
| } |
| }, |
| "_update_policy": { |
| "total": 557.8499920080017, |
| "count": 457, |
| "self": 313.7344243169946, |
| "children": { |
| "TorchPPOOptimizer.update": { |
| "total": 244.11556769100707, |
| "count": 22827, |
| "self": 244.11556769100707 |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "trainer_threads": { |
| "total": 9.410000529896934e-07, |
| "count": 1, |
| "self": 9.410000529896934e-07 |
| }, |
| "TrainerController._save_models": { |
| "total": 0.08357072299986612, |
| "count": 1, |
| "self": 0.00148227199952089, |
| "children": { |
| "RLTrainer._checkpoint": { |
| "total": 0.08208845100034523, |
| "count": 1, |
| "self": 0.08208845100034523 |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
