{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.6408207416534424, "min": 0.636042594909668, "max": 1.4533050060272217, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 19450.19140625, "min": 18867.568359375, "max": 44087.4609375, "count": 33 }, "Pyramids.Step.mean": { "value": 989967.0, "min": 29952.0, "max": 989967.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989967.0, "min": 29952.0, "max": 989967.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.34317871928215027, "min": -0.11139141023159027, "max": 0.37908679246902466, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 88.88328552246094, "min": -26.733938217163086, "max": 101.00526428222656, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.8146594762802124, "min": -0.4114195704460144, "max": 0.8146594762802124, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 210.99681091308594, "min": -106.14624786376953, "max": 210.99681091308594, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06500562419699106, "min": 0.06500562419699106, "max": 0.07492626529894822, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9100787387578749, "min": 0.5244838570926376, "max": 1.0415800327318718, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.0948010394931771, "min": 0.0004719591016884409, "max": 0.0948010394931771, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 1.3272145529044794, "min": 0.004719591016884409, "max": 1.3272145529044794, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.500440357028567e-06, "min": 7.500440357028567e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010500616499839994, "min": 0.00010500616499839994, "max": 0.0033820268726577995, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.1025001142857143, "min": 0.1025001142857143, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4350016000000003, "min": 1.3886848, "max": 2.5273422, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025976141714285705, "min": 0.00025976141714285705, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003636659839999999, "min": 0.003636659839999999, "max": 0.11276148578000002, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.009081761352717876, "min": 0.009081761352717876, "max": 0.343353271484375, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.12714466452598572, "min": 0.12714466452598572, "max": 2.403472900390625, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 526.8245614035088, "min": 480.4375, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30029.0, "min": 15984.0, "max": 32729.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.2887856752744742, "min": -1.0000000521540642, "max": 1.363399976835801, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 72.17199781537056, "min": -30.99940161406994, "max": 88.62099849432707, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.2887856752744742, "min": -1.0000000521540642, "max": 1.363399976835801, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 72.17199781537056, "min": -30.99940161406994, "max": 88.62099849432707, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.05051289933284612, "min": 0.048677051853379595, "max": 6.762861746363342, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.8287223626393825, "min": 2.8287223626393825, "max": 108.20578794181347, "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": "1715258420", "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": "1715260639" }, "total": 2219.634278802, "count": 1, "self": 0.4766806039997391, "children": { "run_training.setup": { "total": 0.04899637300013637, "count": 1, "self": 0.04899637300013637 }, "TrainerController.start_learning": { "total": 2219.1086018250003, "count": 1, "self": 1.4339892189186685, "children": { "TrainerController._reset_env": { "total": 2.1335217650000686, "count": 1, "self": 2.1335217650000686 }, "TrainerController.advance": { "total": 2215.4481966400817, "count": 63387, "self": 1.4791394441117518, "children": { "env_step": { "total": 1576.261986976991, "count": 63387, "self": 1437.8097381539894, "children": { "SubprocessEnvManager._take_step": { "total": 137.5340426350001, "count": 63387, "self": 4.989647182025465, "children": { "TorchPolicy.evaluate": { "total": 132.54439545297464, "count": 62576, "self": 132.54439545297464 } } }, "workers": { "total": 0.9182061880014771, "count": 63387, "self": 0.0, "children": { "worker_root": { "total": 2213.9200193200677, "count": 63387, "is_parallel": true, "self": 906.5650662850348, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0020428319999155065, "count": 1, "is_parallel": true, "self": 0.0005865930002073583, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014562389997081482, "count": 8, "is_parallel": true, "self": 0.0014562389997081482 } } }, "UnityEnvironment.step": { "total": 0.0617389199999252, "count": 1, "is_parallel": true, "self": 0.0008692559999872174, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005332279999947787, "count": 1, "is_parallel": true, "self": 0.0005332279999947787 }, "communicator.exchange": { "total": 0.05783696200001032, "count": 1, "is_parallel": true, "self": 0.05783696200001032 }, "steps_from_proto": { "total": 0.0024994739999328885, "count": 1, "is_parallel": true, "self": 0.0005274959999042039, "children": { "_process_rank_one_or_two_observation": { "total": 0.0019719780000286846, "count": 8, "is_parallel": true, "self": 0.0019719780000286846 } } } } } } }, "UnityEnvironment.step": { "total": 1307.3549530350328, "count": 63386, "is_parallel": true, "self": 34.60919737602444, "children": { "UnityEnvironment._generate_step_input": { "total": 24.737312253006166, "count": 63386, "is_parallel": true, "self": 24.737312253006166 }, "communicator.exchange": { "total": 1143.8248884220125, "count": 63386, "is_parallel": true, "self": 1143.8248884220125 }, "steps_from_proto": { "total": 104.18355498398978, "count": 63386, "is_parallel": true, "self": 21.565820242910377, "children": { "_process_rank_one_or_two_observation": { "total": 82.6177347410794, "count": 507088, "is_parallel": true, "self": 82.6177347410794 } } } } } } } } } } }, "trainer_advance": { "total": 637.707070218979, "count": 63387, "self": 2.7479016629295074, "children": { "process_trajectory": { "total": 131.58526170404866, "count": 63387, "self": 131.38422167804856, "children": { "RLTrainer._checkpoint": { "total": 0.20104002600010062, "count": 2, "self": 0.20104002600010062 } } }, "_update_policy": { "total": 503.3739068520008, "count": 443, "self": 297.4812731639852, "children": { "TorchPPOOptimizer.update": { "total": 205.89263368801562, "count": 22869, "self": 205.89263368801562 } } } } } } }, "trainer_threads": { "total": 9.649997991800774e-07, "count": 1, "self": 9.649997991800774e-07 }, "TrainerController._save_models": { "total": 0.09289323599978161, "count": 1, "self": 0.0015804529998604266, "children": { "RLTrainer._checkpoint": { "total": 0.09131278299992118, "count": 1, "self": 0.09131278299992118 } } } } } } }