Engineering a Conformant Probabilistic Planner

TL;DR

This paper introduces Probapop, a partial-order probabilistic planner that uses adapted heuristics for probabilistic domains, demonstrating its performance in the IPC-4 competition.

Contribution

It presents a novel conformant probabilistic planner, Probapop, with new heuristic adaptations for probabilistic planning domains.

Findings

Probapop successfully competed in IPC-4 blind track.

Heuristics based on probability of success improve planning efficiency.

Challenges in adapting heuristics for probabilistic domains are discussed.

Abstract

We present a partial-order, conformant, probabilistic planner, Probapop which competed in the blind track of the Probabilistic Planning Competition in IPC-4. We explain how we adapt distance based heuristics for use with probabilistic domains. Probapop also incorporates heuristics based on probability of success. We explain the successes and difficulties encountered during the design and implementation of Probapop.