Compact Modeling in Constraint Programming with Hybrid Tables

摘要

Hybrid tables, also referred to as `smart' in the literature, represent a valuable modeling technique within Constraint Programming (CP). These tables allow us to handle disjunctive cases (constraining expressions) in a compact and structured way, by authorizing tuples (table entries) to contain simple unary and binary arithmetic restrictions (similar to internal constraints). In this paper, we show the practical interest of using hybrid tables for planning-like combinatorial puzzles, when the transition from one state to the next can be encoded by a single hybrid table. Experimental results show that these hybrid models exhibit greater compactness and efficiency in solving compared to their conventional counterparts.