Learning Heuristic Functions with Graph Neural Networks for Numeric Planning
Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (43) · 36172-36179
DOI: 10.1609/aaai.v40i43.40935 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Valerio Borelli und 3 weiteren Autor:innen.
Abstract (Originalsprache)
In this paper, we investigate the application of heuristics based on Graph Neural Networks (GNNs) to lifted numeric planning problems, an area that has been relatively unexplored. Building upon the GNN approach for learning general policies proposed by Ståhlberg, Bonet, and Geffner (2022b), we extend the architecture to make it 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, enabling the construction of a finite structure. Instead of learning general policies, we train our models to serve as heuristics within a best-first search algorithm. We explore various 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 computational cost compared to state-of-the-art heuristics.
Zitieren
APA
Borelli, V., Gerevini, A., Scala, E., & Serina, I. (2026). Learning Heuristic Functions with Graph Neural Networks for Numeric Planning. Proceedings of the AAAI Conference on Artificial Intelligence, 40(43), 36172-36179. https://doi.org/10.1609/aaai.v40i43.40935
Vancouver
Borelli V, Gerevini A, Scala E, Serina I. Learning Heuristic Functions with Graph Neural Networks for Numeric Planning. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(43):36172-36179. doi:10.1609/aaai.v40i43.40935
BibTeX
@article{Borelli2026,
author = {Borelli, Valerio and Gerevini, Alfonso and Scala, Enrico and Serina, Ivan},
title = {Learning Heuristic Functions with Graph Neural Networks for Numeric Planning},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2026},
volume = {40},
number = {43},
pages = {36172--36179},
doi = {10.1609/aaai.v40i43.40935}
}
EUVIMED