Intelligent search strategies based on adaptive Constraint Handling Rules

TL;DR

This paper evaluates adaptive Constraint Handling Rules (CHR) strategies for solving Constraint Satisfaction Problems, demonstrating that intelligent search methods like conflict-directed backjumping can significantly reduce search steps and runtime compared to traditional methods.

Contribution

It introduces and compares adaptive CHR-based search strategies, including conflict-directed backjumping and dynamic backtracking, with traditional chronological backtracking in solving CSPs.

Findings

Conflict-directed backjumping reduces search steps significantly.

Java implementations outperform SICStus Prolog in runtime.

Intelligent search strategies can be more efficient than traditional methods.

Abstract

The most advanced implementation of adaptive constraint processing with Constraint Handling Rules (CHR) allows the application of intelligent search strategies to solve Constraint Satisfaction Problems (CSP). This presentation compares an improved version of conflict-directed backjumping and two variants of dynamic backtracking with respect to chronological backtracking on some of the AIM instances which are a benchmark set of random 3-SAT problems. A CHR implementation of a Boolean constraint solver combined with these different search strategies in Java is thus being compared with a CHR implementation of the same Boolean constraint solver combined with chronological backtracking in SICStus Prolog. This comparison shows that the addition of ``intelligence'' to the search process may reduce the number of search steps dramatically. Furthermore, the runtime of their Java implementations is in most cases faster than the implementations of chronological backtracking. More specifically, conflict-directed backjumping is even faster than the SICStus Prolog implementation of chronological backtracking, although our Java implementation of CHR lacks the optimisations made in the SICStus Prolog system. To appear in Theory and Practice of Logic Programming (TPLP).