Abstract
In spite of the improvements in the performance of many solvers for model-based languages, it is still possible for the search algorithm to focus on the wrong areas of the search space, preventing the solver from returning a solution in an acceptable amount of time. This prospect is a real concern e.g. in an industrial setting, where users typically expect consistent performance. To overcome this problem, we propose a framework that allows learning and using domain-specific heuristics in the solvers. The learning is done offline, on representative instances from the target domain, and the learned heuristics are then used for choice-point selection. In this paper we focus on Answer Set Programming (ASP) solvers. In our experiments, the introduction of domain-specific heuristics improved performance quite substantially on hard instances, and in particular made overall performance more consistent by reducing the number of cases in which the solver timed out.