PASCAL - Pattern Analysis, Statistical Modelling and Computational Learning

Optimal control as a graphical model inference problem
Bert Kappen, Vicenc Gomez and Manfred Opper
Machien Learning Journal pp. 1-11, 2012.

Abstract

Abstract We reformulate a class of non-linear stochastic optimal control problems introduced by Todorov (in Advances in Neural Information Processing Systems, vol. 19, pp. 1369–1376, 2007) as a Kullback-Leibler (KL) minimization problem. As a result, the optimal control computation reduces to an inference computation and approximate inference methods can be applied to efficiently compute approximate optimal controls. We show how this KL control theory contains the path integral control method as a special case. We provide an example of a block stacking task and a multi-agent cooperative game where we demonstrate how approximate inference can be successfully applied to instances that are too complex for exact computation. We discuss the relation of the KL control approach to other inference approaches to control.

EPrint Type:Article
Additional Information:Keywords: Optimal control · Uncontrolled dynamics · Kullback-Leibler divergence · Graphical model · Approximate inference · Cluster variation method · Belief propagation
Project Keyword:Project Keyword UNSPECIFIED
Subjects:Computational, Information-Theoretic Learning with Statistics
Learning/Statistics & Optimisation
ID Code:9332
Deposited By:Bert Kappen
Deposited On:16 March 2012