{"title":"BPS spectroscopy with reinforcement learning","authors":"Federico Carta , Asa Gauntlett , Finley Griffin , Yang-Hui He","doi":"10.1016/j.physletb.2025.139646","DOIUrl":null,"url":null,"abstract":"<div><div>We apply reinforcement learning (RL) to establish whether at a given position in the Coulomb branch of the moduli space of a 4d <span><math><mi>N</mi><mo>=</mo><mn>2</mn></math></span> quantum field theory (QFT) the BPS spectrum is finite. If it is, we furthermore determine the full BPS spectrum at such point in moduli space. We demonstrate that using a RL model one can efficiently determine the suitable sequence of quiver mutations of the BPS quiver that will generate the full BPS spectrum. We analyse the performance of the RL model on random BPS quivers and show that it converges to a solution various orders of magnitude faster than a systematic brute-force scan. As a result, we show that our algorithm can be used to identify all minimal chambers of a given <span><math><mi>N</mi><mo>=</mo><mn>2</mn></math></span> QFT, a task previously intractable with computer scanning. As an example, we recover all minimal chambers of the <span><math><mtext>SU</mtext><mo>(</mo><mn>2</mn><mo>)</mo></math></span> <span><math><msub><mrow><mi>N</mi></mrow><mrow><mi>f</mi></mrow></msub><mo>=</mo><mn>4</mn></math></span> gauge theory, and discover new minimal chambers for theories that can be realized by IIB geometric engineering.</div></div>","PeriodicalId":20162,"journal":{"name":"Physics Letters B","volume":"868 ","pages":"Article 139646"},"PeriodicalIF":4.5000,"publicationDate":"2025-06-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Physics Letters B","FirstCategoryId":"101","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0370269325004071","RegionNum":2,"RegionCategory":"物理与天体物理","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"ASTRONOMY & ASTROPHYSICS","Score":null,"Total":0}
引用次数: 0
Abstract
We apply reinforcement learning (RL) to establish whether at a given position in the Coulomb branch of the moduli space of a 4d quantum field theory (QFT) the BPS spectrum is finite. If it is, we furthermore determine the full BPS spectrum at such point in moduli space. We demonstrate that using a RL model one can efficiently determine the suitable sequence of quiver mutations of the BPS quiver that will generate the full BPS spectrum. We analyse the performance of the RL model on random BPS quivers and show that it converges to a solution various orders of magnitude faster than a systematic brute-force scan. As a result, we show that our algorithm can be used to identify all minimal chambers of a given QFT, a task previously intractable with computer scanning. As an example, we recover all minimal chambers of the gauge theory, and discover new minimal chambers for theories that can be realized by IIB geometric engineering.
期刊介绍:
Physics Letters B ensures the rapid publication of important new results in particle physics, nuclear physics and cosmology. Specialized editors are responsible for contributions in experimental nuclear physics, theoretical nuclear physics, experimental high-energy physics, theoretical high-energy physics, and astrophysics.