Optimal control as a graphical model inference problem

Details Optimal control as a graphical model inference problem Optimal control as a graphical model inference problem

2009-01-06

arxiv.org/abs/0901.0633v3

Mathematics

Optimization and Control

26 pages, 12 Figures; Machine Learning Journal (2012)

Scientific paper

10.1007/s10994-012-5278-7

We reformulate a class of non-linear stochastic optimal control problems introduced by Todorov (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.

Affiliated with

Also associated with

No associations

Rating

Optimal control as a graphical model inference problem does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.

If you have personal experience with Optimal control as a graphical model inference problem, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Optimal control as a graphical model inference problem will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-632280