| { |
| "name": "root", |
| "gauges": { |
| "Pyramids.Policy.Entropy.mean": { |
| "value": 0.37858104705810547, |
| "min": 0.37858104705810547, |
| "max": 1.5315675735473633, |
| "count": 37 |
| }, |
| "Pyramids.Policy.Entropy.sum": { |
| "value": 11308.97265625, |
| "min": 11308.97265625, |
| "max": 46461.6328125, |
| "count": 37 |
| }, |
| "Pyramids.Step.mean": { |
| "value": 1109909.0, |
| "min": 29952.0, |
| "max": 1109909.0, |
| "count": 37 |
| }, |
| "Pyramids.Step.sum": { |
| "value": 1109909.0, |
| "min": 29952.0, |
| "max": 1109909.0, |
| "count": 37 |
| }, |
| "Pyramids.Policy.ExtrinsicValueEstimate.mean": { |
| "value": 0.6644173264503479, |
| "min": -0.27855029702186584, |
| "max": 0.6910170912742615, |
| "count": 37 |
| }, |
| "Pyramids.Policy.ExtrinsicValueEstimate.sum": { |
| "value": 188.69451904296875, |
| "min": -66.01641845703125, |
| "max": 200.39495849609375, |
| "count": 37 |
| }, |
| "Pyramids.Policy.RndValueEstimate.mean": { |
| "value": -0.005646523088216782, |
| "min": -0.005646523088216782, |
| "max": 0.18868683278560638, |
| "count": 37 |
| }, |
| "Pyramids.Policy.RndValueEstimate.sum": { |
| "value": -1.6036125421524048, |
| "min": -1.6036125421524048, |
| "max": 45.28483963012695, |
| "count": 37 |
| }, |
| "Pyramids.Losses.PolicyLoss.mean": { |
| "value": 0.06763679030605477, |
| "min": 0.0631826339383787, |
| "max": 0.07442784279760083, |
| "count": 37 |
| }, |
| "Pyramids.Losses.PolicyLoss.sum": { |
| "value": 1.0145518545908214, |
| "min": 0.497527035192256, |
| "max": 1.0790887281090917, |
| "count": 37 |
| }, |
| "Pyramids.Losses.ValueLoss.mean": { |
| "value": 0.016082859862146116, |
| "min": 0.00018845308282612076, |
| "max": 0.01642923192399898, |
| "count": 37 |
| }, |
| "Pyramids.Losses.ValueLoss.sum": { |
| "value": 0.24124289793219172, |
| "min": 0.0013191715797828453, |
| "max": 0.24124289793219172, |
| "count": 37 |
| }, |
| "Pyramids.Policy.LearningRate.mean": { |
| "value": 0.00019049626983458888, |
| "min": 0.00019049626983458888, |
| "max": 0.00029838354339596195, |
| "count": 37 |
| }, |
| "Pyramids.Policy.LearningRate.sum": { |
| "value": 0.0028574440475188333, |
| "min": 0.002027104024298666, |
| "max": 0.0038475183174939654, |
| "count": 37 |
| }, |
| "Pyramids.Policy.Epsilon.mean": { |
| "value": 0.16349874444444443, |
| "min": 0.16349874444444443, |
| "max": 0.19946118095238097, |
| "count": 37 |
| }, |
| "Pyramids.Policy.Epsilon.sum": { |
| "value": 2.4524811666666664, |
| "min": 1.3757013333333334, |
| "max": 2.7825060333333336, |
| "count": 37 |
| }, |
| "Pyramids.Policy.Beta.mean": { |
| "value": 0.00635352457, |
| "min": 0.00635352457, |
| "max": 0.009946171977142856, |
| "count": 37 |
| }, |
| "Pyramids.Policy.Beta.sum": { |
| "value": 0.09530286854999999, |
| "min": 0.06757256319999999, |
| "max": 0.12827235273, |
| "count": 37 |
| }, |
| "Pyramids.Losses.RNDLoss.mean": { |
| "value": 0.009203771129250526, |
| "min": 0.009203771129250526, |
| "max": 0.4092442989349365, |
| "count": 37 |
| }, |
| "Pyramids.Losses.RNDLoss.sum": { |
| "value": 0.13805656135082245, |
| "min": 0.13325971364974976, |
| "max": 2.8647100925445557, |
| "count": 37 |
| }, |
| "Pyramids.Environment.EpisodeLength.mean": { |
| "value": 244.61206896551724, |
| "min": 244.61206896551724, |
| "max": 999.0, |
| "count": 37 |
| }, |
| "Pyramids.Environment.EpisodeLength.sum": { |
| "value": 28375.0, |
| "min": 15984.0, |
| "max": 33354.0, |
| "count": 37 |
| }, |
| "Pyramids.Environment.CumulativeReward.mean": { |
| "value": 1.7011333146156409, |
| "min": -1.0000000521540642, |
| "max": 1.7267875946992266, |
| "count": 37 |
| }, |
| "Pyramids.Environment.CumulativeReward.sum": { |
| "value": 199.03259781002998, |
| "min": -32.000001668930054, |
| "max": 199.03259781002998, |
| "count": 37 |
| }, |
| "Pyramids.Policy.ExtrinsicReward.mean": { |
| "value": 1.7011333146156409, |
| "min": -1.0000000521540642, |
| "max": 1.7267875946992266, |
| "count": 37 |
| }, |
| "Pyramids.Policy.ExtrinsicReward.sum": { |
| "value": 199.03259781002998, |
| "min": -32.000001668930054, |
| "max": 199.03259781002998, |
| "count": 37 |
| }, |
| "Pyramids.Policy.RndReward.mean": { |
| "value": 0.023620226536566515, |
| "min": 0.023620226536566515, |
| "max": 9.217512246221304, |
| "count": 37 |
| }, |
| "Pyramids.Policy.RndReward.sum": { |
| "value": 2.7635665047782823, |
| "min": 2.7635665047782823, |
| "max": 147.48019593954086, |
| "count": 37 |
| }, |
| "Pyramids.IsTraining.mean": { |
| "value": 1.0, |
| "min": 1.0, |
| "max": 1.0, |
| "count": 37 |
| }, |
| "Pyramids.IsTraining.sum": { |
| "value": 1.0, |
| "min": 1.0, |
| "max": 1.0, |
| "count": 37 |
| } |
| }, |
| "metadata": { |
| "timer_format_version": "0.1.0", |
| "start_time_seconds": "1762764091", |
| "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": "1762766475" |
| }, |
| "total": 2384.229232875, |
| "count": 1, |
| "self": 0.4171892660001504, |
| "children": { |
| "run_training.setup": { |
| "total": 0.023365422999972907, |
| "count": 1, |
| "self": 0.023365422999972907 |
| }, |
| "TrainerController.start_learning": { |
| "total": 2383.7886781859997, |
| "count": 1, |
| "self": 1.4275899559888785, |
| "children": { |
| "TrainerController._reset_env": { |
| "total": 3.6347986460000357, |
| "count": 1, |
| "self": 3.6347986460000357 |
| }, |
| "TrainerController.advance": { |
| "total": 2378.6000708890106, |
| "count": 72052, |
| "self": 1.4498560410384016, |
| "children": { |
| "env_step": { |
| "total": 1655.8936341860083, |
| "count": 72052, |
| "self": 1496.9800982259858, |
| "children": { |
| "SubprocessEnvManager._take_step": { |
| "total": 158.0502516830204, |
| "count": 72052, |
| "self": 4.927611075032701, |
| "children": { |
| "TorchPolicy.evaluate": { |
| "total": 153.1226406079877, |
| "count": 70329, |
| "self": 153.1226406079877 |
| } |
| } |
| }, |
| "workers": { |
| "total": 0.8632842770020943, |
| "count": 72051, |
| "self": 0.0, |
| "children": { |
| "worker_root": { |
| "total": 2376.6875558560328, |
| "count": 72051, |
| "is_parallel": true, |
| "self": 1004.5849519031246, |
| "children": { |
| "run_training.setup": { |
| "total": 0.0, |
| "count": 0, |
| "is_parallel": true, |
| "self": 0.0, |
| "children": { |
| "steps_from_proto": { |
| "total": 0.005853953000041656, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.004017084999986764, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 0.001836868000054892, |
| "count": 8, |
| "is_parallel": true, |
| "self": 0.001836868000054892 |
| } |
| } |
| }, |
| "UnityEnvironment.step": { |
| "total": 0.04961734500000148, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.0005386440000165749, |
| "children": { |
| "UnityEnvironment._generate_step_input": { |
| "total": 0.00045530499994583806, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.00045530499994583806 |
| }, |
| "communicator.exchange": { |
| "total": 0.04702569400001266, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.04702569400001266 |
| }, |
| "steps_from_proto": { |
| "total": 0.001597702000026402, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.0003328970000211484, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 0.0012648050000052535, |
| "count": 8, |
| "is_parallel": true, |
| "self": 0.0012648050000052535 |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "UnityEnvironment.step": { |
| "total": 1372.102603952908, |
| "count": 72050, |
| "is_parallel": true, |
| "self": 36.53047862991639, |
| "children": { |
| "UnityEnvironment._generate_step_input": { |
| "total": 24.323907187026975, |
| "count": 72050, |
| "is_parallel": true, |
| "self": 24.323907187026975 |
| }, |
| "communicator.exchange": { |
| "total": 1198.8162572950155, |
| "count": 72050, |
| "is_parallel": true, |
| "self": 1198.8162572950155 |
| }, |
| "steps_from_proto": { |
| "total": 112.43196084094927, |
| "count": 72050, |
| "is_parallel": true, |
| "self": 23.394349923097366, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 89.03761091785191, |
| "count": 576400, |
| "is_parallel": true, |
| "self": 89.03761091785191 |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "trainer_advance": { |
| "total": 721.256580661964, |
| "count": 72051, |
| "self": 2.7418394259836987, |
| "children": { |
| "process_trajectory": { |
| "total": 134.95383822398014, |
| "count": 72051, |
| "self": 134.74401425697977, |
| "children": { |
| "RLTrainer._checkpoint": { |
| "total": 0.20982396700037498, |
| "count": 2, |
| "self": 0.20982396700037498 |
| } |
| } |
| }, |
| "_update_policy": { |
| "total": 583.5609030120002, |
| "count": 492, |
| "self": 323.22917797700495, |
| "children": { |
| "TorchPPOOptimizer.update": { |
| "total": 260.3317250349952, |
| "count": 25695, |
| "self": 260.3317250349952 |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "trainer_threads": { |
| "total": 1.2300001799303573e-06, |
| "count": 1, |
| "self": 1.2300001799303573e-06 |
| }, |
| "TrainerController._save_models": { |
| "total": 0.12621746500008157, |
| "count": 1, |
| "self": 0.0013180570003896719, |
| "children": { |
| "RLTrainer._checkpoint": { |
| "total": 0.1248994079996919, |
| "count": 1, |
| "self": 0.1248994079996919 |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
