{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.5032317042350769, "min": 0.48783302307128906, "max": 1.4052824974060059, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 15024.486328125, "min": 14642.7958984375, "max": 32014.6796875, "count": 33 }, "Pyramids.Step.mean": { "value": 989954.0, "min": 29952.0, "max": 989954.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989954.0, "min": 29952.0, "max": 989954.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.23423583805561066, "min": -0.13060688972473145, "max": 0.29978105425834656, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 60.198612213134766, "min": -31.476259231567383, "max": 77.94307708740234, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.014698714949190617, "min": -0.0001770851667970419, "max": 0.43297699093818665, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 3.7775697708129883, "min": -0.045687973499298096, "max": 80.90855407714844, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06832533799939632, "min": 0.06546820892413677, "max": 0.0705766391779651, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9565547319915484, "min": 0.26895508741232005, "max": 1.057345730854043, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.011186378650622306, "min": 0.00027094015793847366, "max": 0.011186378650622306, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.1566093011087123, "min": 0.0035222220532001576, "max": 0.1626825869328362, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.195254744471428e-06, "min": 7.195254744471428e-06, "max": 0.00029388480203839995, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010073356642259998, "min": 0.00010073356642259998, "max": 0.003376515174494999, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10239838571428572, "min": 0.10239838571428572, "max": 0.1979616, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4335774000000001, "min": 0.7918464, "max": 2.4430687000000004, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00024959873285714294, "min": 0.00024959873285714294, "max": 0.00979636384, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003494382260000001, "min": 0.003494382260000001, "max": 0.1125679495, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.014127911068499088, "min": 0.014127911068499088, "max": 0.3064412474632263, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.19779075682163239, "min": 0.19779075682163239, "max": 1.7120411396026611, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 600.0784313725491, "min": 520.3888888888889, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30604.0, "min": 15984.0, "max": 33919.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 0.9684156534426352, "min": -1.0000000521540642, "max": 1.183225898830979, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 49.3891983255744, "min": -30.995201610028744, "max": 63.894198536872864, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 0.9684156534426352, "min": -1.0000000521540642, "max": 1.183225898830979, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 49.3891983255744, "min": -30.995201610028744, "max": 63.894198536872864, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.08710368909055878, "min": 0.08372828757812924, "max": 3.996903594583273, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 4.442288143618498, "min": 4.3072825799754355, "max": 63.95045751333237, "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": "1722596668", "python_version": "3.10.12 (main, Jul 29 2024, 16:56:48) [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 --resume", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.3.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1722598870" }, "total": 2201.384442583, "count": 1, "self": 0.5380541719996472, "children": { "run_training.setup": { "total": 0.05258541700004571, "count": 1, "self": 0.05258541700004571 }, "TrainerController.start_learning": { "total": 2200.793802994, "count": 1, "self": 1.3802115891480753, "children": { "TrainerController._reset_env": { "total": 2.1322384960003546, "count": 1, "self": 2.1322384960003546 }, "TrainerController.advance": { "total": 2197.1987525578525, "count": 62736, "self": 1.4046175168018635, "children": { "env_step": { "total": 1576.8071024969918, "count": 62736, "self": 1443.9154912961862, "children": { "SubprocessEnvManager._take_step": { "total": 132.06496854784518, "count": 62736, "self": 4.681367966797097, "children": { "TorchPolicy.evaluate": { "total": 127.38360058104809, "count": 61944, "self": 127.38360058104809 } } }, "workers": { "total": 0.826642652960345, "count": 62736, "self": 0.0, "children": { "worker_root": { "total": 2195.701025025926, "count": 62736, "is_parallel": true, "self": 873.4038963110197, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002116510999712773, "count": 1, "is_parallel": true, "self": 0.0006839950001449324, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014325159995678405, "count": 8, "is_parallel": true, "self": 0.0014325159995678405 } } }, "UnityEnvironment.step": { "total": 0.04816528399987874, "count": 1, "is_parallel": true, "self": 0.0006433989997276512, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004596919998220983, "count": 1, "is_parallel": true, "self": 0.0004596919998220983 }, "communicator.exchange": { "total": 0.04531101300017326, "count": 1, "is_parallel": true, "self": 0.04531101300017326 }, "steps_from_proto": { "total": 0.0017511800001557276, "count": 1, "is_parallel": true, "self": 0.00037308400078472914, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013780959993709985, "count": 8, "is_parallel": true, "self": 0.0013780959993709985 } } } } } } }, "UnityEnvironment.step": { "total": 1322.2971287149062, "count": 62735, "is_parallel": true, "self": 33.34118377760478, "children": { "UnityEnvironment._generate_step_input": { "total": 23.58642543505266, "count": 62735, "is_parallel": true, "self": 23.58642543505266 }, "communicator.exchange": { "total": 1166.3172018161508, "count": 62735, "is_parallel": true, "self": 1166.3172018161508 }, "steps_from_proto": { "total": 99.05231768609792, "count": 62735, "is_parallel": true, "self": 20.347783920181882, "children": { "_process_rank_one_or_two_observation": { "total": 78.70453376591604, "count": 501880, "is_parallel": true, "self": 78.70453376591604 } } } } } } } } } } }, "trainer_advance": { "total": 618.9870325440588, "count": 62736, "self": 2.5270645890882406, "children": { "process_trajectory": { "total": 127.56066954296512, "count": 62736, "self": 127.36193948196524, "children": { "RLTrainer._checkpoint": { "total": 0.19873006099987833, "count": 2, "self": 0.19873006099987833 } } }, "_update_policy": { "total": 488.89929841200546, "count": 445, "self": 289.3877783760113, "children": { "TorchPPOOptimizer.update": { "total": 199.51152003599418, "count": 22575, "self": 199.51152003599418 } } } } } } }, "trainer_threads": { "total": 9.549994501867332e-07, "count": 1, "self": 9.549994501867332e-07 }, "TrainerController._save_models": { "total": 0.08259939599975041, "count": 1, "self": 0.0018695460003073094, "children": { "RLTrainer._checkpoint": { "total": 0.0807298499994431, "count": 1, "self": 0.0807298499994431 } } } } } } }