Branes with Brains: Exploring String Vacua with Deep Reinforcement Learning

Abstract

We propose deep reinforcement learning as a model-free method for exploring the landscape of string vacua. As a concrete application, we utilize an artificial intelligence agent known as an asynchronous advantage actor-critic to explore type IIA compactifications with intersecting D6-branes. As different string background configurations are explored by changing D6-brane configurations, the agent receives rewards and punishments related to string consistency conditions and proximity to Standard Model vacua. These are in turn utilized to update the agent's policy and value neural networks to improve its behavior. By reinforcement learning, the agent's performance in both tasks is significantly improved, and for some tasks it finds a factor of O(200) more solutions than a random walker. In one case, we demonstrate that the agent learns a human-derived strategy for finding consistent string models. In another case, where no human-derived strategy exists, the agent learns a genuinely new strategy that achieves the same goal twice as efficiently per unit time. Our results demonstrate that the agent learns to solve various string theory consistency conditions simultaneously, which are phrased in terms of non-linear, coupled Diophantine equations.

57 pages, 10 figures

References in corpus (34)

• The statistics of string/M theory vacua
• Counting Flux Vacua
• Reinforcement Learning in Different Phases of Quantum Control
• Neural Combinatorial Optimization with Reinforcement Learning
• D-brane probes, RR tadpole cancellation and K-theory charge
• One in a Billion: MSSM-like D-Brane Statistics
• Computational complexity of the landscape I
• Supersymmetric Pati-Salam Models from Intersecting D6-branes: A Road to the Standard Model
• Machine Learning of Calabi-Yau Volumes
• Machine Learning in the String Landscape
• The landscape of intersecting brane models
• Evolving neural networks with genetic algorithms to study the String Landscape
• Statistics of M theory Vacua
• Machine Learning CICY Threefolds
• Deep Learning and Holographic QCD
• On Algorithmic Universality in F-theory Compactifications
• Machine Learning Line Bundle Cohomologies of Hypersurfaces in Toric Varieties
• Scanning the skeleton of the 4D F-theory landscape
• The F-theory geometry with most flux vacua
• Deep learning in the heterotic orbifold landscape
• Deep Learning the Hyperbolic Volume of a Knot
• Computational Complexity of Vacua and Near-Vacua in Field and String Theory
• The Moduli Space of Heterotic Line Bundle Models: a Case Study for the Tetra-Quadric
• Vacuum Selection from Cosmology on Networks of String Geometries
• GANs for generating EFT models
• Estimating Calabi-Yau Hypersurface and Triangulation Counts with Equation Learners
• On the computation of non-perturbative effective potentials in the string theory landscape -- IIB/F-theory perspective
• Infinite number of MSSMs from heterotic line bundles?
• Learning non-Higgsable gauge groups in 4D F-theory
• Artificial Neural Network in Cosmic Landscape
• Machine learning for bounce calculation
• Learning to Inflate
• On finiteness of Type IIB compactifications: Magnetized branes on elliptic Calabi-Yau threefolds
• Diversity in the Tail of the Intersecting Brane Landscape

Cited by in corpus (50)

• When does reinforcement learning stand out in quantum control? A comparative study on state preparation
• Searching the Landscape of Flux Vacua with Genetic Algorithms
• Moduli Stabilization in Asymptotic Flux Compactifications
• The Calabi-Yau Landscape: from Geometry, to Physics, to Machine-Learning
• Solving Conformal Field Theories with Artificial Intelligence
• Machine learning for complete intersection Calabi-Yau manifolds: a methodological study
• Explore and Exploit with Heterotic Line Bundle Models
• Evolving Heterotic Gauge Backgrounds: Genetic Algorithms versus Reinforcement Learning
• Deep learning and k-means clustering in heterotic string vacua with line bundles
• Statistical Predictions in String Theory and Deep Generative Models
• Accessibility Measure for Eternal Inflation: Dynamical Criticality and Higgs Metastability
• Revealing systematics in phenomenologically viable flux vacua with reinforcement learning
• Hilbert Series, Machine Learning, and Applications to Physics
• Heterotic String Model Building with Monad Bundles and Reinforcement Learning
• Contrast data mining for the MSSM from strings
• Deep multi-task mining Calabi-Yau four-folds
• Line bundle cohomologies on CICYs with Picard number two
• Applying machine learning to the Calabi-Yau orientifolds with string vacua
• Breeding realistic D-brane models
• The landscape of promising non-supersymmetric string models
• Disentangling a Deep Learned Volume Formula
• Transforming the Bootstrap: Using Transformers to Compute Scattering Amplitudes in Planar N = 4 Super Yang-Mills Theory
• Lectures on the Calabi-Yau Landscape
• The Final Model Building for the Supersymmetric Pati-Salam Models from Intersecting D6-Branes
• Predicting the orbifold origin of the MSSM
• 134 Billion Intersecting Brane Models
• The Complete Search for the Supersymmetric Pati-Salam Models from Intersecting D6-Branes
• Graph Laplacians, Riemannian Manifolds and their Machine-Learning
• Ising Machines for Diophantine Problems in Physics
• Noise-Robust End-to-End Quantum Control using Deep Autoregressive Policy Networks
• Brill-Noether-general Limit Root Bundles: Absence of vector-like Exotics in F-theory Standard Models
• Characterizing 4-string contact interaction using machine learning
• String-scale Gauge Coupling Relations in the Supersymmetric Pati-Salam Models from Intersecting D6-branes
• Universes as Big Data
• Machine Learning on generalized Complete Intersection Calabi-Yau Manifolds
• Conformal Bootstrap with Reinforcement Learning
• Generative AI for Brane Configurations and Coamoeba
• Calabi-Yau Four/Five/Six-folds as ${\mathbb{P}}_{\text{w}}^n$ Hypersurfaces: Machine Learning, Approximation, and Generation
• Improved statistics for F-theory standard models
• Particle Physics Model Building with Reinforcement Learning
• Testing Swampland Conjectures with Machine Learning
• Machine learning and serving of discrete field theories -- when artificial intelligence meets the discrete universe
• Learning Principle of Least Action with Reinforcement Learning
• Root bundles: Applications to F-theory Standard Models
• Probing the Structure of String Theory Vacua with Genetic Algorithms and Reinforcement Learning
• Learning 3-Manifold Triangulations
• Vafa-Witten Theory: Invariants, Floer Homologies, Higgs Bundles, a Geometric Langlands Correspondence, and Categorification (String Math 2022 Proceedings)
• Graph Reinforcement Learning for Exploring BSM Model Spaces
• String Model Building, Reinforcement Learning and Genetic Algorithms
• Exploring the holographic entropy cone via reinforcement learning