Optimal Control as a Graphical Model Inference Problem

Authors

  • Hilbert Kappen Radboud University
  • Vicenç Gomez Radboud University
  • Manfred Opper TU Berlin

DOI:

https://doi.org/10.1609/icaps.v23i1.13573

Keywords:

Optimal Control, Kullback-Leibler, Graphical Model, Approximate Inference, Belief Propagation

Abstract

In this paper we show the identification between stochastic optimal control computation and probabilistic inference on a graphical model for certain class of control problems. We refer to these problems as Kullback-Leibler (KL) control problems. We illustrate how KL control can be used to model a multi-agent cooperative game for which optimal control can be approximated using belief propagation when exact inference is unfeasible.

Downloads

Published

2013-06-02

How to Cite

Kappen, H., Gomez, V., & Opper, M. (2013). Optimal Control as a Graphical Model Inference Problem. Proceedings of the International Conference on Automated Planning and Scheduling, 23(1), 472-473. https://doi.org/10.1609/icaps.v23i1.13573

Issue

Vol. 23 (2013): Twenty-Third International Conference on Automated Planning and Scheduling

Section

Journal Presentation Track