{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.17709867656230927, "min": 0.17709867656230927, "max": 1.365432858467102, "count": 100 }, "Pyramids.Policy.Entropy.sum": { "value": 5307.29296875, "min": 5307.29296875, "max": 41421.76953125, "count": 100 }, "Pyramids.Step.mean": { "value": 2999922.0, "min": 29952.0, "max": 2999922.0, "count": 100 }, "Pyramids.Step.sum": { "value": 2999922.0, "min": 29952.0, "max": 2999922.0, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.7084278464317322, "min": -0.10809285938739777, "max": 0.8643080592155457, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 207.56936645507812, "min": -25.95266342163086, "max": 264.478271484375, "count": 100 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.010320375673472881, "min": -0.005453253164887428, "max": 0.676671028137207, "count": 100 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 3.0238699913024902, "min": -1.5501084327697754, "max": 160.37103271484375, "count": 100 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06952286520195115, "min": 0.06372349346320841, "max": 0.07468585786980339, "count": 100 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9733201128273161, "min": 0.48630299194580096, "max": 1.0789749146742729, "count": 100 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.016240210391028985, "min": 5.644087260798002e-05, "max": 0.016886676780938845, "count": 100 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.22736294547440578, "min": 0.0007337313439037403, "max": 0.24694983276034088, "count": 100 }, "Pyramids.Policy.LearningRate.mean": { "value": 1.5633137646428612e-06, "min": 1.5633137646428612e-06, "max": 0.00029838354339596195, "count": 100 }, "Pyramids.Policy.LearningRate.sum": { "value": 2.1886392705000056e-05, "min": 2.1886392705000056e-05, "max": 0.004011042662985799, "count": 100 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10052107142857143, "min": 0.10052107142857143, "max": 0.19946118095238097, "count": 100 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.407295, "min": 1.3962282666666668, "max": 2.7370142, "count": 100 }, "Pyramids.Policy.Beta.mean": { "value": 6.205503571428583e-05, "min": 6.205503571428583e-05, "max": 0.009946171977142856, "count": 100 }, "Pyramids.Policy.Beta.sum": { "value": 0.0008687705000000017, "min": 0.0008687705000000017, "max": 0.13370771858000002, "count": 100 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.009031159803271294, "min": 0.009031159803271294, "max": 0.6894707083702087, "count": 100 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.1264362335205078, "min": 0.1264362335205078, "max": 4.826294898986816, "count": 100 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 271.83898305084745, "min": 207.77205882352942, "max": 999.0, "count": 100 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 32077.0, "min": 15984.0, "max": 33930.0, "count": 100 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.660354220261008, "min": -1.0000000521540642, "max": 1.7870689546239786, "count": 100 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 195.92179799079895, "min": -30.996201619505882, "max": 259.1249984204769, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.660354220261008, "min": -1.0000000521540642, "max": 1.7870689546239786, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 195.92179799079895, "min": -30.996201619505882, "max": 259.1249984204769, "count": 100 }, "Pyramids.Policy.RndReward.mean": { "value": 0.025521636635688592, "min": 0.02016998506286812, "max": 13.802874190732837, "count": 100 }, "Pyramids.Policy.RndReward.sum": { "value": 3.0115531230112538, "min": 2.6826080133614596, "max": 220.8459870517254, "count": 100 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 100 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 100 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1711834840", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]", "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": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.2.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1711844976" }, "total": 10136.150012088001, "count": 1, "self": 0.6789710170014587, "children": { "run_training.setup": { "total": 0.07302902599985828, "count": 1, "self": 0.07302902599985828 }, "TrainerController.start_learning": { "total": 10135.398012045, "count": 1, "self": 7.1605779948204145, "children": { "TrainerController._reset_env": { "total": 3.516723989000184, "count": 1, "self": 3.516723989000184 }, "TrainerController.advance": { "total": 10124.62859509718, "count": 194133, "self": 7.5451453455898445, "children": { "env_step": { "total": 6996.80988440948, "count": 194133, "self": 6518.572538196704, "children": { "SubprocessEnvManager._take_step": { "total": 473.75655193647026, "count": 194133, "self": 20.77977152739004, "children": { "TorchPolicy.evaluate": { "total": 452.9767804090802, "count": 187548, "self": 452.9767804090802 } } }, "workers": { "total": 4.4807942763059145, "count": 194133, "self": 0.0, "children": { "worker_root": { "total": 10116.501160929005, "count": 194133, "is_parallel": true, "self": 4155.654746417178, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005983532000300329, "count": 1, "is_parallel": true, "self": 0.001561221999963891, "children": { "_process_rank_one_or_two_observation": { "total": 0.004422310000336438, "count": 8, "is_parallel": true, "self": 0.004422310000336438 } } }, "UnityEnvironment.step": { "total": 0.07749171300019952, "count": 1, "is_parallel": true, "self": 0.0008029989999158715, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004957430001013563, "count": 1, "is_parallel": true, "self": 0.0004957430001013563 }, "communicator.exchange": { "total": 0.07407809799997267, "count": 1, "is_parallel": true, "self": 0.07407809799997267 }, "steps_from_proto": { "total": 0.002114873000209627, "count": 1, "is_parallel": true, "self": 0.0004661220013986167, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016487509988110105, "count": 8, "is_parallel": true, "self": 0.0016487509988110105 } } } } } } }, "UnityEnvironment.step": { "total": 5960.846414511827, "count": 194132, "is_parallel": true, "self": 154.89370998613686, "children": { "UnityEnvironment._generate_step_input": { "total": 84.50958788597973, "count": 194132, "is_parallel": true, "self": 84.50958788597973 }, "communicator.exchange": { "total": 5319.669166562671, "count": 194132, "is_parallel": true, "self": 5319.669166562671 }, "steps_from_proto": { "total": 401.77395007703944, "count": 194132, "is_parallel": true, "self": 86.28197022118047, "children": { "_process_rank_one_or_two_observation": { "total": 315.491979855859, "count": 1553056, "is_parallel": true, "self": 315.491979855859 } } } } } } } } } } }, "trainer_advance": { "total": 3120.2735653421105, "count": 194133, "self": 14.406493017050252, "children": { "process_trajectory": { "total": 495.32430628206475, "count": 194133, "self": 494.7835064410642, "children": { "RLTrainer._checkpoint": { "total": 0.5407998410005348, "count": 6, "self": 0.5407998410005348 } } }, "_update_policy": { "total": 2610.5427660429955, "count": 1393, "self": 1059.152118239998, "children": { "TorchPPOOptimizer.update": { "total": 1551.3906478029976, "count": 68301, "self": 1551.3906478029976 } } } } } } }, "trainer_threads": { "total": 1.0339990694774315e-06, "count": 1, "self": 1.0339990694774315e-06 }, "TrainerController._save_models": { "total": 0.09211393000077805, "count": 1, "self": 0.0020587260005413555, "children": { "RLTrainer._checkpoint": { "total": 0.0900552040002367, "count": 1, "self": 0.0900552040002367 } } } } } } }