2021/11/22 by Alex Cole, Cole, Alex, Sven Krippendorf +5 · 3 citations
Computer Science · Mathematics · Physics and Astronomy · #Advanced Data Storage Technologies #Algorithm #Algorithms and Data Compression #Archaeology #Artificial intelligence #Computational Physics and Python Applications #Computer science #Context (archaeology) #FOS: Physical sciences #Geography #Geometry #High Energy Physics - Theory (hep-th) #Homogeneous space #Mathematics #Parallel Computing and Optimization Techniques #Physics #Reinforcement learning #String (physics) #String searching algorithm #String theory #Theoretical computer science #Theoretical physics #hep-th
paper · pdf · doi:10.48550/arxiv.2111.11466
published in arXiv (Cornell University) (Cornell University) · 7 pages, 2 figures, accepted at NeurIPS workshop on Machine Learning and the Physical Sciences
arxiv created 2021/11/22 · openalex publication_date 2021/11/22 · arxiv updated 2021/11/24 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/08
Identifying string theory vacua with desired physical properties at low energies requires searching through high-dimensional solution spaces - collectively referred to as the string landscape. We highlight that this search problem is amenable to reinforcement learning and genetic algorithms. In the context of flux vacua, we are able to reveal novel features (suggesting previously unidentified symmetries) in the string theory solutions required for properties such as the string coupling. In order to identify these features robustly, we combine results from both search methods, which we argue is imperative for reducing sampling bias.