This paper presents results on applying a version of the DOLPHIN search-control learning system to speed up a partial-order planner. DOLPHIN integrates explanation-based and inductive learning techniques to acquire effective clause-selection rules for Prolog programs. A version of the UCPOP partial-order planning algorithm has been implemented as a Prolog program and DOLPHIN used to automatically learn domain-specific search control rules that help eliminate backtracking. The resulting system is shown to produce significant speedup in several planning domains.

PDF, PS

In Malik Ghallab and Alfredo Milani, editors, New Directions in AI Planning, 129-140, Amsterdam, 1996. IOS Press.

@InCollection{estlin:bkchapter96, title={Hybrid Learning of Search Control for Partial-Order Planning}, author={Tara A. Estlin and Raymond J. Mooney}, booktitle={New Directions in AI Planning}, editor={Malik Ghallab and Alfredo Milani}, address={Amsterdam}, publisher={IOS Press}, pages={129-140}, url="http://www.cs.utexas.edu/users/ai-lab/pub-view.php?PubID=51510", year={1996} }