Evolving Heterotic Gauge Backgrounds: Genetic Algorithms versus Reinforcement Learning

2021/10/26 by Steven Abel, Andrei Constantin, Thomas R. Harvey +2 · 27 citations
Engineering · Mathematics · Physics and Astronomy · #Algorithm #Archaeology #Artificial intelligence #Black Holes and Theoretical Physics #Computer science #Engineering #Gauge (firearms) #Geography #Heterotic string theory #Mathematics #Monad (category theory) #Particle physics #Particle physics theoretical and experimental studies #Physics #Pure mathematics #Quantum Chromodynamics and Particle Interactions #Reinforcement #Reinforcement learning #String (physics) #String theory #Structural engineering #Theoretical physics #hep-th

paper · pdf · open access · doi:10.1002/prop.202200034

published in Fortschritte der Physik 70(5) (Wiley) · 29 pages, 12 figures

arxiv created 2021/10/26 · openalex publication_date 2022/03/16 · arxiv updated 2022/05/18 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/05

Abstract

The immensity of the string landscape and the difficulty of identifying solutions that match the observed features of particle physics have raised serious questions about the predictive power of string theory. Modern methods of optimisation and search can, however, significantly improve the prospects of constructing the standard model in string theory. In this paper we scrutinise a corner of the heterotic string landscape consisting of compactifications on Calabi-Yau three-folds with monad bundles and show that genetic algorithms can be successfully used to generate anomaly-free supersymmetric SO(10) GUTs with three families of fermions that have the right ingredients to accommodate the standard model. We compare this method with reinforcement learning and find that the two methods have similar efficacy but somewhat complementary characteristics.

Cited by

• Enumerating Calabi‐Yau Manifolds: Placing Bounds on the Number of Diffeomorphism Classes in the Kreuzer‐Skarke List
• Reinforcement Learning techniques for the flavor problem in particle physics
• Sampling String Vacua Using Generative Models
• Machine Learning the 6d Supergravity Landscape

Related

• String Model Building, Reinforcement Learning and Genetic Algorithms
• Probing the Structure of String Theory Vacua with Genetic Algorithms and Reinforcement Learning
• Decoding Nature with Nature's Tools: Heterotic Line Bundle Models of Particle Physics with Genetic Algorithms and Quantum Annealing
• Intelligent Explorations of the String Theory Landscape
• Exploring Line Bundle Standard Models with Transformers