Kernel-Based Optimal Control: An Infinitesimal Generator Approach
This provides a novel operator-theoretic framework for data-driven optimal control, addressing a fundamental problem in robotics and control theory.
The paper tackles optimal control of nonlinear stochastic systems by developing a data-driven approach that learns the infinitesimal generator of controlled stochastic diffusions in reproducing kernel Hilbert spaces. Numerical experiments demonstrate advantages over existing methods for synthetic differential equations and simulated robotic systems.
This paper presents a novel operator-theoretic approach for optimal control of nonlinear stochastic systems within reproducing kernel Hilbert spaces. Our learning framework leverages data samples of system dynamics and stage cost functions, with only control penalties and constraints provided. The proposed method directly learns the infinitesimal generator of a controlled stochastic diffusion in an infinite-dimensional hypothesis space. We demonstrate that our approach seamlessly integrates with modern convex operator-theoretic Hamilton-Jacobi-Bellman recursions, enabling a data-driven solution to the optimal control problems. Furthermore, our learning framework includes nonparametric estimators for uncontrolled infinitesimal generators as a special case. Numerical experiments, ranging from synthetic differential equations to simulated robotic systems, showcase the advantages of our approach compared to both modern data-driven and classical nonlinear programming methods for optimal control.