Neural Network Heuristic Functions: Taking Confidence into Account

Heller, Daniel and Ferber, Patrick and Bitterwolf, Julian and Hein, Matthias and Hoffmann, Jörg. (2022) Neural Network Heuristic Functions: Taking Confidence into Account. In: Proceedings of the Fifteenth International Symposium on Combinatorial Search (SoCS2022). pp. 223-228.

[img] PDF - Accepted Version

Official URL: https://edoc.unibas.ch/93508/

Downloads: Statistics Overview


Neural networks (NN) are increasingly investigated in AI Planning, and are used successfully to learn heuristic functions. NNs commonly not only predict a value, but also output a confidence in this prediction. From the perspective of heuristic search with NN heuristics, it is a natural idea to take this into account, e.g. falling back to a standard heuristic where confidence is low. We contribute an empirical study of this idea. We design search methods which prune nodes, or switch between search queues, based on the confidence of NNs. We furthermore explore the possibility of out-of-distribution (OOD) training, which tries to reduce the overconfidence of NNs on inputs different to the training distribution. In experiments on IPC benchmarks, we find that our search methods improve coverage over standard methods, and that OOD training has the desired effect in terms of prediction accuracy and confidence, though its impact on search seems marginal.
Faculties and Departments:05 Faculty of Science > Departement Mathematik und Informatik > Informatik > Artificial Intelligence (Helmert)
UniBasel Contributors:Ferber, Patrick
Item Type:Conference or Workshop Item, refereed
Conference or workshop item Subtype:Conference Paper
Publisher:AAAI Press
Note:Publication type according to Uni Basel Research Database: Conference paper
Identification Number:
edoc DOI:
Last Modified:29 Mar 2023 12:34
Deposited On:15 Feb 2023 11:12

Repository Staff Only: item control page