MultiSTOP: Solving Functional Equations with Reinforcement Learning

Alessandro Trenta, Davide Bacciu, Andrea Cossu, Pietro Ferrero, MultiSTOP: Solving Functional Equations with Reinforcement Learning, ICLR 2024 Workshop on AI4DifferentialEquations In Science. DOI: 10.48550/arXiv.2404.14909

Abstract: We develop MultiSTOP, a Reinforcement Learning framework for solving functional equations in physics. This new methodology is also able to find actual numerical solutions instead of bounds. 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.