Optimal Control as a Graphical Model Inference Problem

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.

Authors

• Hilbert J. Kappen
• Vicenç Gómez
• Manfred Opper

Keywords

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