Learning Heuristic Functions with Graph Neural Networks for Numeric Planning (Extended Abstract)

In this paper, we investigate the application of heuristics based on Graph Neural Networks (GNNs) to lifted numeric planning problems, an area that is still relatively unexplored. Building upon the GNN approach for learning general poli cies proposed by St˚ahlberg, Bonet, and Geffner (2022), we propose an architecture sensitive to the numeric components inherent in the planning problems we address. We achieve this by observing that, although the state space of a numeric planning problem is infinite, the finite subgoal structure of the problem can be incorporated into the architecture, allow ing for the construction of only a finite structure. Instead of learning general policies, we train our models to function as a heuristic within a best-first search algorithm. We explore var ious configurations of this architecture and demonstrate that the resulting heuristics are highly informative and, in certain domains, offer a better trade-off between guidance and com putational cost compared to other heuristics.