English

MultiSTOP: Solving Functional Equations with Reinforcement Learning

Machine Learning 2024-04-24 v1 High Energy Physics - Theory

Abstract

We develop MultiSTOP, a Reinforcement Learning framework for solving functional equations in physics. This new methodology produces actual numerical solutions instead of bounds on them. We extend the original BootSTOP algorithm by adding multiple constraints derived from domain-specific knowledge, even in integral form, to improve the accuracy of the solution. We investigate a particular equation in a one-dimensional Conformal Field Theory.

Keywords

Cite

@article{arxiv.2404.14909,
  title  = {MultiSTOP: Solving Functional Equations with Reinforcement Learning},
  author = {Alessandro Trenta and Davide Bacciu and Andrea Cossu and Pietro Ferrero},
  journal= {arXiv preprint arXiv:2404.14909},
  year   = {2024}
}

Comments

ICLR 2024 Workshop on AI4DifferentialEquations In Science

R2 v1 2026-06-28T16:03:28.484Z