| { |
| "name": "root", |
| "gauges": { |
| "Pyramids.Policy.Entropy.mean": { |
| "value": 0.2962254583835602, |
| "min": 0.2962254583835602, |
| "max": 1.4413392543792725, |
| "count": 53 |
| }, |
| "Pyramids.Policy.Entropy.sum": { |
| "value": 8863.0654296875, |
| "min": 8863.0654296875, |
| "max": 43724.46875, |
| "count": 53 |
| }, |
| "Pyramids.Step.mean": { |
| "value": 1589938.0, |
| "min": 29909.0, |
| "max": 1589938.0, |
| "count": 53 |
| }, |
| "Pyramids.Step.sum": { |
| "value": 1589938.0, |
| "min": 29909.0, |
| "max": 1589938.0, |
| "count": 53 |
| }, |
| "Pyramids.Policy.ExtrinsicValueEstimate.mean": { |
| "value": 0.6544503569602966, |
| "min": -0.13386553525924683, |
| "max": 0.6965250968933105, |
| "count": 53 |
| }, |
| "Pyramids.Policy.ExtrinsicValueEstimate.sum": { |
| "value": 183.24609375, |
| "min": -31.726131439208984, |
| "max": 202.6887969970703, |
| "count": 53 |
| }, |
| "Pyramids.Policy.RndValueEstimate.mean": { |
| "value": 0.008541206829249859, |
| "min": -0.004894384648650885, |
| "max": 0.26739275455474854, |
| "count": 53 |
| }, |
| "Pyramids.Policy.RndValueEstimate.sum": { |
| "value": 2.39153790473938, |
| "min": -1.3312726020812988, |
| "max": 64.441650390625, |
| "count": 53 |
| }, |
| "Pyramids.Losses.PolicyLoss.mean": { |
| "value": 0.06791415828463089, |
| "min": 0.06414387037279574, |
| "max": 0.07688687492990888, |
| "count": 53 |
| }, |
| "Pyramids.Losses.PolicyLoss.sum": { |
| "value": 0.9507982159848325, |
| "min": 0.5697386697521994, |
| "max": 1.0656994126751953, |
| "count": 53 |
| }, |
| "Pyramids.Losses.ValueLoss.mean": { |
| "value": 0.012795513520402545, |
| "min": 3.397792195702487e-05, |
| "max": 0.015672207884823108, |
| "count": 53 |
| }, |
| "Pyramids.Losses.ValueLoss.sum": { |
| "value": 0.17913718928563563, |
| "min": 0.0004756909073983481, |
| "max": 0.2194109103875235, |
| "count": 53 |
| }, |
| "Pyramids.Policy.LearningRate.mean": { |
| "value": 0.00023738079061909047, |
| "min": 0.00023738079061909047, |
| "max": 0.0004973384796989708, |
| "count": 53 |
| }, |
| "Pyramids.Policy.LearningRate.sum": { |
| "value": 0.0033233310686672664, |
| "min": 0.0033233310686672664, |
| "max": 0.006615196243627433, |
| "count": 53 |
| }, |
| "Pyramids.Policy.Epsilon.mean": { |
| "value": 0.14747614761904762, |
| "min": 0.14747614761904762, |
| "max": 0.19946769583333335, |
| "count": 53 |
| }, |
| "Pyramids.Policy.Epsilon.sum": { |
| "value": 2.0646660666666667, |
| "min": 1.5957415666666668, |
| "max": 2.812432333333333, |
| "count": 53 |
| }, |
| "Pyramids.Policy.Beta.mean": { |
| "value": 0.004752867147142857, |
| "min": 0.004752867147142857, |
| "max": 0.009946822813750002, |
| "count": 53 |
| }, |
| "Pyramids.Policy.Beta.sum": { |
| "value": 0.06654014006, |
| "min": 0.06654014006, |
| "max": 0.13231161941, |
| "count": 53 |
| }, |
| "Pyramids.Losses.RNDLoss.mean": { |
| "value": 0.007482690270990133, |
| "min": 0.00721547519788146, |
| "max": 0.436746746301651, |
| "count": 53 |
| }, |
| "Pyramids.Losses.RNDLoss.sum": { |
| "value": 0.10475766658782959, |
| "min": 0.10175766795873642, |
| "max": 3.493973970413208, |
| "count": 53 |
| }, |
| "Pyramids.Environment.EpisodeLength.mean": { |
| "value": 325.57954545454544, |
| "min": 269.962962962963, |
| "max": 999.0, |
| "count": 53 |
| }, |
| "Pyramids.Environment.EpisodeLength.sum": { |
| "value": 28651.0, |
| "min": 16836.0, |
| "max": 32353.0, |
| "count": 53 |
| }, |
| "Pyramids.Environment.CumulativeReward.mean": { |
| "value": 1.6516840730539777, |
| "min": -0.9999375520274043, |
| "max": 1.7115166570853304, |
| "count": 53 |
| }, |
| "Pyramids.Environment.CumulativeReward.sum": { |
| "value": 145.34819842875004, |
| "min": -31.998001664876938, |
| "max": 184.84379896521568, |
| "count": 53 |
| }, |
| "Pyramids.Policy.ExtrinsicReward.mean": { |
| "value": 1.6516840730539777, |
| "min": -0.9999375520274043, |
| "max": 1.7115166570853304, |
| "count": 53 |
| }, |
| "Pyramids.Policy.ExtrinsicReward.sum": { |
| "value": 145.34819842875004, |
| "min": -31.998001664876938, |
| "max": 184.84379896521568, |
| "count": 53 |
| }, |
| "Pyramids.Policy.RndReward.mean": { |
| "value": 0.0254892447956081, |
| "min": 0.02254114387699129, |
| "max": 8.733806723180939, |
| "count": 53 |
| }, |
| "Pyramids.Policy.RndReward.sum": { |
| "value": 2.243053542013513, |
| "min": 2.1806043524379675, |
| "max": 148.47471429407597, |
| "count": 53 |
| }, |
| "Pyramids.IsTraining.mean": { |
| "value": 1.0, |
| "min": 1.0, |
| "max": 1.0, |
| "count": 53 |
| }, |
| "Pyramids.IsTraining.sum": { |
| "value": 1.0, |
| "min": 1.0, |
| "max": 1.0, |
| "count": 53 |
| } |
| }, |
| "metadata": { |
| "timer_format_version": "0.1.0", |
| "start_time_seconds": "1775031231", |
| "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=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": "1775035212" |
| }, |
| "total": 3980.6763782649996, |
| "count": 1, |
| "self": 10.006416220999654, |
| "children": { |
| "run_training.setup": { |
| "total": 0.028090636000001723, |
| "count": 1, |
| "self": 0.028090636000001723 |
| }, |
| "TrainerController.start_learning": { |
| "total": 3970.641871408, |
| "count": 1, |
| "self": 2.4213678390669884, |
| "children": { |
| "TrainerController._reset_env": { |
| "total": 3.33845897599997, |
| "count": 1, |
| "self": 3.33845897599997 |
| }, |
| "TrainerController.advance": { |
| "total": 3964.8810305189327, |
| "count": 102987, |
| "self": 2.5214897649411796, |
| "children": { |
| "env_step": { |
| "total": 2806.907762745952, |
| "count": 102987, |
| "self": 2534.716633191863, |
| "children": { |
| "SubprocessEnvManager._take_step": { |
| "total": 270.7582673090251, |
| "count": 102987, |
| "self": 8.265638740045233, |
| "children": { |
| "TorchPolicy.evaluate": { |
| "total": 262.49262856897985, |
| "count": 100278, |
| "self": 262.49262856897985 |
| } |
| } |
| }, |
| "workers": { |
| "total": 1.4328622450638022, |
| "count": 102986, |
| "self": 0.0, |
| "children": { |
| "worker_root": { |
| "total": 3960.5372310080293, |
| "count": 102986, |
| "is_parallel": true, |
| "self": 1633.9936543630079, |
| "children": { |
| "run_training.setup": { |
| "total": 0.0, |
| "count": 0, |
| "is_parallel": true, |
| "self": 0.0, |
| "children": { |
| "steps_from_proto": { |
| "total": 0.0056379989999868485, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.004151015000161351, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 0.0014869839998254974, |
| "count": 8, |
| "is_parallel": true, |
| "self": 0.0014869839998254974 |
| } |
| } |
| }, |
| "UnityEnvironment.step": { |
| "total": 0.054338541999982226, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.0005978759999152317, |
| "children": { |
| "UnityEnvironment._generate_step_input": { |
| "total": 0.0005928280000944142, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.0005928280000944142 |
| }, |
| "communicator.exchange": { |
| "total": 0.05145581499994023, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.05145581499994023 |
| }, |
| "steps_from_proto": { |
| "total": 0.00169202300003235, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.00037534900013724837, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 0.0013166739998951016, |
| "count": 8, |
| "is_parallel": true, |
| "self": 0.0013166739998951016 |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "UnityEnvironment.step": { |
| "total": 2326.5435766450214, |
| "count": 102985, |
| "is_parallel": true, |
| "self": 60.062692219290966, |
| "children": { |
| "UnityEnvironment._generate_step_input": { |
| "total": 42.53172544591439, |
| "count": 102985, |
| "is_parallel": true, |
| "self": 42.53172544591439 |
| }, |
| "communicator.exchange": { |
| "total": 2026.3852583548462, |
| "count": 102985, |
| "is_parallel": true, |
| "self": 2026.3852583548462 |
| }, |
| "steps_from_proto": { |
| "total": 197.56390062496973, |
| "count": 102985, |
| "is_parallel": true, |
| "self": 41.09069134977722, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 156.47320927519252, |
| "count": 823880, |
| "is_parallel": true, |
| "self": 156.47320927519252 |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "trainer_advance": { |
| "total": 1155.4517780080396, |
| "count": 102986, |
| "self": 4.614294611997593, |
| "children": { |
| "process_trajectory": { |
| "total": 224.8879458480401, |
| "count": 102986, |
| "self": 224.5504359730396, |
| "children": { |
| "RLTrainer._checkpoint": { |
| "total": 0.33750987500047813, |
| "count": 3, |
| "self": 0.33750987500047813 |
| } |
| } |
| }, |
| "_update_policy": { |
| "total": 925.949537548002, |
| "count": 738, |
| "self": 510.6775665590261, |
| "children": { |
| "TorchPPOOptimizer.update": { |
| "total": 415.2719709889759, |
| "count": 36546, |
| "self": 415.2719709889759 |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "trainer_threads": { |
| "total": 1.452000105928164e-06, |
| "count": 1, |
| "self": 1.452000105928164e-06 |
| }, |
| "TrainerController._save_models": { |
| "total": 0.0010126220004167408, |
| "count": 1, |
| "self": 2.2865000573801808e-05, |
| "children": { |
| "RLTrainer._checkpoint": { |
| "total": 0.000989756999842939, |
| "count": 1, |
| "self": 0.000989756999842939 |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
