Learning Rewrite Rules versus Search Control Rules to Improve Plan Quality

Abstract

Domain independent planners can produce better-quality plans through the use of domain-specific knowledge, typically encoded as search control rules. The planning-by-rewriting approach has been proposed as an alternative technique for improving plan quality. We present a system that automatically learns plan rewriting rules and compare it with a system that automatically learns search control rules for partial order planners. Our results indicate that learning search control rules is a better choice than learning rewrite rules.