On learning control knowledge for a HTN-POP hybrid planner

Abstract

In this paper we present a learning method that is able to automatically acquire control knowledge for a hybrid HTN-POP planner called HYBIS. HYBIS decomposes a problem in subproblems using either a default method or a user-defined decomposition method. Then, at each level of abstraction, it generates a plan at that level using a POCL (Partial Order Causal Link) planning technique. Our learning approach builds on HAMLET, a system that learns control knowledge for a total order non-linear planner (PRODIGY4.0). In this paper, we focus on the operator selection problem for the POP component of HYBIS, which is very important for efficiency purposes.