Learning Interpretable Heuristics for WalkSAT

TL;DR

This paper introduces a reinforcement learning approach to automatically learn heuristics for WalkSAT, improving its performance on various SAT instance distributions by tailoring variable scoring and noise parameters.

Contribution

It presents a novel method for learning instance-specific heuristics for WalkSAT using reinforcement learning, enhancing its effectiveness across different SAT distributions.

Findings

Improved WalkSAT performance over baseline and previous learned heuristics.

Effective adaptation of heuristics to different SAT instance distributions.

Reinforcement learning successfully optimizes variable scoring and noise parameters.

Abstract

Local search algorithms are well-known methods for solving large, hard instances of the satisfiability problem (SAT). The performance of these algorithms crucially depends on heuristics for setting noise parameters and scoring variables. The optimal setting for these heuristics varies for different instance distributions. In this paper, we present an approach for learning effective variable scoring functions and noise parameters by using reinforcement learning. We consider satisfiability problems from different instance distributions and learn specialized heuristics for each of them. Our experimental results show improvements with respect to both a WalkSAT baseline and another local search learned heuristic.