Markov Chain Monte Carlo for Koopman-based Optimal Control: Technical Report
Jo\~ao Hespanha, Kerem Camsari

TL;DR
This paper introduces an MCMC algorithm utilizing Gibbs sampling with parallel tempering to efficiently solve nonlinear optimal control problems by leveraging Koopman operator theory, demonstrated through a video game example.
Contribution
It presents a novel MCMC approach that exploits Koopman linearity for scalable nonlinear control, enabling efficient computation for high-dimensional systems.
Findings
Efficient control solution for high-dimensional nonlinear systems.
Significant computational savings using Koopman-based MCMC.
Successful demonstration on a video game control problem.
Abstract
We propose a Markov Chain Monte Carlo (MCMC) algorithm based on Gibbs sampling with parallel tempering to solve nonlinear optimal control problems. The algorithm is applicable to nonlinear systems with dynamics that can be approximately represented by a finite dimensional Koopman model, potentially with high dimension. This algorithm exploits linearity of the Koopman representation to achieve significant computational saving for large lifted states. We use a video-game to illustrate the use of the method.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
