This paper compares three commitment strategies for HTN planning: (1) a strategy that delays variable bindings as much as possible; (2) a strategy in which no non-primitive task is expanded until all variable constraints are committed; and (3) a strategy that chooses between expansion and variable instantiation based on the number of branches that will be created in the search tree. Our results show that while there existplanning domains in which the first two strategies do well, the third does well over a broader range of planning domains.
Reiko Tsuneto, Kutluhan Erol, James A. Hendler, Da