Configurable Heuristic Adaptation for Improving Best First Search in AI Planning

Automated planning is one of the most prominent AI challenges. In the last few decades, there has been a great deal of activity in designing planning techniques and planning engines, with a focus on forward state-space search. Despite the ubiquitous use of heuristics in AI planning, these techniques are susceptible to being easily trapped by undetected dead ends and huge search plateaus. In this paper we introduce a highly configurable heuristic adaptation process based on the idea of dynamically penalising unpromising actions when an inconsistency in the heuristic evaluation is detected; its aim is to reduce the bias affecting specific actions, thereby encouraging exploration by the search process and adding diversity in the neighbourhood selection process. Our extensive experimental analysis demonstrates that the proposed heuristic can be configured to improve significantly the performance of best first search planning on a range of benchmark domains.