Generalizing the Role of Determinization in Probabilistic Planning

TL;DR

This paper explores how tailoring determinization strategies to specific probabilistic planning domains can improve planning efficiency and introduces a new planner, FF-LAO*, that outperforms existing methods on benchmark problems.

Contribution

It demonstrates that learning domain-specific determinization can enhance probabilistic planning and integrates probabilistic reasoning into planning when determinization alone is insufficient.

Findings

Learning good determinization improves planning performance.

Incorporating probabilistic reasoning enhances planning accuracy.

FF-LAO* outperforms state-of-the-art probabilistic planners on benchmarks.

Abstract

The stochastic shortest path problem (SSP) is a highly expressive model for probabilistic planning. The computational hardness of SSPs has sparked interest in determinization-based planners that can quickly solve large problems. However, existing methods employ a simplistic approach to determinization. In particular, they ignore the possibility of tailoring the determinization to the specific characteristics of the target domain. In this work we examine this question, by showing that learning a good determinization for a planning domain can be done efficiently and can improve performance. Moreover, we show how to directly incorporate probabilistic reasoning into the planning problem when a good determinization is not sufficient by itself. Based on these insights, we introduce a planner, FF-LAO*, that outperforms state-of-the-art probabilistic planners on several well-known competition benchmarks.