Formula Neural Networks as Action Policies in Safety-Critical Planning: An Empirical Evaluation
Proceedings of the International Symposium on Combinatorial Search · 14.08.2026 · 19 (1) · 240-245
DOI: 10.1609/socs.v19i1.43095 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the International Symposium on Combinatorial Search, online erschienen am 14.08.2026. Verfasst von Victor Scherer Putrich und 5 weiteren Autor:innen.
Abstract (Originalsprache)
Formula neural networks (FNNs) are a recently proposed alternative to neural networks (NNs), with Boolean neuron values and hidden-layer nodes defined as propositional formulas over the previous layer. FNNs have been successfully applied to classification and, compared to standard NNs, offer greater interpretability. Here we show that they are also a promising alternative for learning action policies and that they can be more amenable to formal verification. We consider planning under uncertainty, with the objective to reach the goal while avoiding unsafe states. We adapt a recently proposed NN policy safety verification algorithm to FNNs. Our experiments show that, compared to NNs, FNNs can often learn competitive policies while being much faster to verify.
Zitieren
APA
Putrich, V. S., Bauerschmidt, T. N., Jain, C., Lin, S., Hoffmann, J., & Valera, I. (2026). Formula Neural Networks as Action Policies in Safety-Critical Planning: An Empirical Evaluation. Proceedings of the International Symposium on Combinatorial Search, 19(1), 240-245. https://doi.org/10.1609/socs.v19i1.43095
Vancouver
Putrich VS, Bauerschmidt TN, Jain C, Lin S, Hoffmann J, Valera I. Formula Neural Networks as Action Policies in Safety-Critical Planning: An Empirical Evaluation. Proceedings of the International Symposium on Combinatorial Search. 2026;19(1):240-245. doi:10.1609/socs.v19i1.43095
BibTeX
@article{Putrich2026,
author = {Putrich, Victor Scherer and Bauerschmidt, Tim Nico and Jain, Chaahat and Lin, Songtuan and Hoffmann, Joerg and Valera, Isabel},
title = {Formula Neural Networks as Action Policies in Safety-Critical Planning: An Empirical Evaluation},
journal = {Proceedings of the International Symposium on Combinatorial Search},
year = {2026},
volume = {19},
number = {1},
pages = {240--245},
doi = {10.1609/socs.v19i1.43095}
}
EUVIMED