| { |
| "name": "root", |
| "gauges": { |
| "Pyramids.Policy.Entropy.mean": { |
| "value": 1.0551501512527466, |
| "min": 1.0551501512527466, |
| "max": 1.471710205078125, |
| "count": 3 |
| }, |
| "Pyramids.Policy.Entropy.sum": { |
| "value": 31603.857421875, |
| "min": 31603.857421875, |
| "max": 44645.80078125, |
| "count": 3 |
| }, |
| "Pyramids.Step.mean": { |
| "value": 89899.0, |
| "min": 29952.0, |
| "max": 89899.0, |
| "count": 3 |
| }, |
| "Pyramids.Step.sum": { |
| "value": 89899.0, |
| "min": 29952.0, |
| "max": 89899.0, |
| "count": 3 |
| }, |
| "Pyramids.Policy.ExtrinsicValueEstimate.mean": { |
| "value": -0.04646223783493042, |
| "min": -0.08037937432527542, |
| "max": -0.04646223783493042, |
| "count": 3 |
| }, |
| "Pyramids.Policy.ExtrinsicValueEstimate.sum": { |
| "value": -11.197399139404297, |
| "min": -19.371429443359375, |
| "max": -11.197399139404297, |
| "count": 3 |
| }, |
| "Pyramids.Policy.RndValueEstimate.mean": { |
| "value": 0.11903563141822815, |
| "min": 0.11903563141822815, |
| "max": 0.2086862325668335, |
| "count": 3 |
| }, |
| "Pyramids.Policy.RndValueEstimate.sum": { |
| "value": 28.68758773803711, |
| "min": 28.68758773803711, |
| "max": 50.29338073730469, |
| "count": 3 |
| }, |
| "Pyramids.Losses.PolicyLoss.mean": { |
| "value": 0.07048715921764999, |
| "min": 0.06934989365609133, |
| "max": 0.07076709297526296, |
| "count": 3 |
| }, |
| "Pyramids.Losses.PolicyLoss.sum": { |
| "value": 0.8458459106117999, |
| "min": 0.4854492555926393, |
| "max": 0.8458459106117999, |
| "count": 3 |
| }, |
| "Pyramids.Losses.ValueLoss.mean": { |
| "value": 0.002388843696757638, |
| "min": 0.0013977638633207987, |
| "max": 0.0029475330914260703, |
| "count": 3 |
| }, |
| "Pyramids.Losses.ValueLoss.sum": { |
| "value": 0.028666124361091658, |
| "min": 0.01118211090656639, |
| "max": 0.028666124361091658, |
| "count": 3 |
| }, |
| "Pyramids.Policy.LearningRate.mean": { |
| "value": 7.719732426758332e-05, |
| "min": 7.719732426758332e-05, |
| "max": 0.0002515063018788571, |
| "count": 3 |
| }, |
| "Pyramids.Policy.LearningRate.sum": { |
| "value": 0.000926367891211, |
| "min": 0.000926367891211, |
| "max": 0.0017605441131519997, |
| "count": 3 |
| }, |
| "Pyramids.Policy.Epsilon.mean": { |
| "value": 0.12573241666666668, |
| "min": 0.12573241666666668, |
| "max": 0.1838354285714286, |
| "count": 3 |
| }, |
| "Pyramids.Policy.Epsilon.sum": { |
| "value": 1.5087890000000002, |
| "min": 1.232816, |
| "max": 1.5087890000000002, |
| "count": 3 |
| }, |
| "Pyramids.Policy.Beta.mean": { |
| "value": 0.002580668425, |
| "min": 0.002580668425, |
| "max": 0.008385159314285713, |
| "count": 3 |
| }, |
| "Pyramids.Policy.Beta.sum": { |
| "value": 0.0309680211, |
| "min": 0.0309680211, |
| "max": 0.058696115199999996, |
| "count": 3 |
| }, |
| "Pyramids.Losses.RNDLoss.mean": { |
| "value": 0.08049110323190689, |
| "min": 0.08049110323190689, |
| "max": 0.31922367215156555, |
| "count": 3 |
| }, |
| "Pyramids.Losses.RNDLoss.sum": { |
| "value": 0.9658932685852051, |
| "min": 0.9532225131988525, |
| "max": 2.2345657348632812, |
| "count": 3 |
| }, |
| "Pyramids.Environment.EpisodeLength.mean": { |
| "value": 977.84375, |
| "min": 977.84375, |
| "max": 999.0, |
| "count": 3 |
| }, |
| "Pyramids.Environment.EpisodeLength.sum": { |
| "value": 31291.0, |
| "min": 15984.0, |
| "max": 32687.0, |
| "count": 3 |
| }, |
| "Pyramids.Environment.CumulativeReward.mean": { |
| "value": -0.7912250482477248, |
| "min": -1.0000000521540642, |
| "max": -0.7912250482477248, |
| "count": 3 |
| }, |
| "Pyramids.Environment.CumulativeReward.sum": { |
| "value": -25.319201543927193, |
| "min": -30.719001576304436, |
| "max": -16.000000834465027, |
| "count": 3 |
| }, |
| "Pyramids.Policy.ExtrinsicReward.mean": { |
| "value": -0.7912250482477248, |
| "min": -1.0000000521540642, |
| "max": -0.7912250482477248, |
| "count": 3 |
| }, |
| "Pyramids.Policy.ExtrinsicReward.sum": { |
| "value": -25.319201543927193, |
| "min": -30.719001576304436, |
| "max": -16.000000834465027, |
| "count": 3 |
| }, |
| "Pyramids.Policy.RndReward.mean": { |
| "value": 0.8931561977369711, |
| "min": 0.8931561977369711, |
| "max": 6.428653261624277, |
| "count": 3 |
| }, |
| "Pyramids.Policy.RndReward.sum": { |
| "value": 28.580998327583075, |
| "min": 28.580998327583075, |
| "max": 102.85845218598843, |
| "count": 3 |
| }, |
| "Pyramids.IsTraining.mean": { |
| "value": 1.0, |
| "min": 1.0, |
| "max": 1.0, |
| "count": 3 |
| }, |
| "Pyramids.IsTraining.sum": { |
| "value": 1.0, |
| "min": 1.0, |
| "max": 1.0, |
| "count": 3 |
| } |
| }, |
| "metadata": { |
| "timer_format_version": "0.1.0", |
| "start_time_seconds": "1728551290", |
| "python_version": "3.10.12 (main, Sep 11 2024, 15:47:36) [GCC 11.4.0]", |
| "command_line_arguments": "/usr/local/bin/mlagents-learn /content/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": "2.4.1+cu121", |
| "numpy_version": "1.23.5", |
| "end_time_seconds": "1728551618" |
| }, |
| "total": 327.9542090379998, |
| "count": 1, |
| "self": 1.1601753789998384, |
| "children": { |
| "run_training.setup": { |
| "total": 0.07427669899993816, |
| "count": 1, |
| "self": 0.07427669899993816 |
| }, |
| "TrainerController.start_learning": { |
| "total": 326.71975696000004, |
| "count": 1, |
| "self": 0.275137764011788, |
| "children": { |
| "TrainerController._reset_env": { |
| "total": 2.5485183159998996, |
| "count": 1, |
| "self": 2.5485183159998996 |
| }, |
| "TrainerController.advance": { |
| "total": 323.7374386219883, |
| "count": 6259, |
| "self": 0.29747651799584673, |
| "children": { |
| "env_step": { |
| "total": 203.02292477798346, |
| "count": 6259, |
| "self": 182.99691592398494, |
| "children": { |
| "SubprocessEnvManager._take_step": { |
| "total": 19.862568272003955, |
| "count": 6259, |
| "self": 0.8040170449980906, |
| "children": { |
| "TorchPolicy.evaluate": { |
| "total": 19.058551227005864, |
| "count": 6256, |
| "self": 19.058551227005864 |
| } |
| } |
| }, |
| "workers": { |
| "total": 0.16344058199456413, |
| "count": 6259, |
| "self": 0.0, |
| "children": { |
| "worker_root": { |
| "total": 324.96217573999843, |
| "count": 6259, |
| "is_parallel": true, |
| "self": 162.89533102898326, |
| "children": { |
| "run_training.setup": { |
| "total": 0.0, |
| "count": 0, |
| "is_parallel": true, |
| "self": 0.0, |
| "children": { |
| "steps_from_proto": { |
| "total": 0.0035766359999342967, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.001267204999749083, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 0.0023094310001852136, |
| "count": 8, |
| "is_parallel": true, |
| "self": 0.0023094310001852136 |
| } |
| } |
| }, |
| "UnityEnvironment.step": { |
| "total": 0.07699351399992338, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.0008906969997042324, |
| "children": { |
| "UnityEnvironment._generate_step_input": { |
| "total": 0.0006388730000708165, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.0006388730000708165 |
| }, |
| "communicator.exchange": { |
| "total": 0.07316940600003363, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.07316940600003363 |
| }, |
| "steps_from_proto": { |
| "total": 0.0022945380001146987, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.0004729669999505859, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 0.0018215710001641128, |
| "count": 8, |
| "is_parallel": true, |
| "self": 0.0018215710001641128 |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "UnityEnvironment.step": { |
| "total": 162.06684471101516, |
| "count": 6258, |
| "is_parallel": true, |
| "self": 5.527420618013139, |
| "children": { |
| "UnityEnvironment._generate_step_input": { |
| "total": 3.2805165519941966, |
| "count": 6258, |
| "is_parallel": true, |
| "self": 3.2805165519941966 |
| }, |
| "communicator.exchange": { |
| "total": 139.53092660800326, |
| "count": 6258, |
| "is_parallel": true, |
| "self": 139.53092660800326 |
| }, |
| "steps_from_proto": { |
| "total": 13.727980933004574, |
| "count": 6258, |
| "is_parallel": true, |
| "self": 3.0713483759877818, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 10.656632557016792, |
| "count": 50064, |
| "is_parallel": true, |
| "self": 10.656632557016792 |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "trainer_advance": { |
| "total": 120.417037326009, |
| "count": 6259, |
| "self": 0.3770606250097899, |
| "children": { |
| "process_trajectory": { |
| "total": 19.300274828998, |
| "count": 6259, |
| "self": 19.300274828998 |
| }, |
| "_update_policy": { |
| "total": 100.7397018720012, |
| "count": 30, |
| "self": 39.74857726899745, |
| "children": { |
| "TorchPPOOptimizer.update": { |
| "total": 60.991124603003755, |
| "count": 2235, |
| "self": 60.991124603003755 |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "trainer_threads": { |
| "total": 2.1299999843904516e-06, |
| "count": 1, |
| "self": 2.1299999843904516e-06 |
| }, |
| "TrainerController._save_models": { |
| "total": 0.15866012800006501, |
| "count": 1, |
| "self": 0.0035896890001367865, |
| "children": { |
| "RLTrainer._checkpoint": { |
| "total": 0.15507043899992823, |
| "count": 1, |
| "self": 0.15507043899992823 |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
