Neural Network Heuristic Functions: Taking Confidence into Account

Authors

  • Daniel Heller Saarland University, Saarland Informatics Campus, Saarbrücken, Germany
  • Patrick Ferber Saarland University, Saarland Informatics Campus, Saarbrücken, Germany University of Basel, Basel, Switzerland
  • Julian Bitterwolf University of Tübingen, Tübingen, Germany
  • Matthias Hein University of Tübingen, Tübingen, Germany
  • Jörg Hoffmann Saarland University, Saarland Informatics Campus, Saarbrücken, Germany German Research Center for Artificial Intelligence (DFKI), Saarbrücken, Germany

Keywords:

Machine And Deep Learning In Search

Abstract

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.

Downloads

Published

2022-07-17