Inducing disjunctive and iterative macro-operators from empirical problem-solving traces provides a more powerful knowledge compilation method than simple linear macro-operators. Whereas earlier work focused on when to create iterative macro-operators, this paper addresses how to form them, combining proven optimization methods such as extraction of loop invariants, with techniques for further optimizing RETEmatch efficiency. The disjunctive and iterative composition processes have been implemented in FERMI and its underlying production system language. Empirical results confirm substantial rule-match speedups and system performance improvements in different application domains.
Peter Shell, Jaime G. Carbonell