Reproducing kernel approach to linear quadratic mean field control problems

TL;DR

This paper introduces a reproducing kernel Hilbert space framework for linear quadratic mean-field control problems, enabling trajectory-based optimization and handling stochastic dynamics without traditional optimal control techniques.

Contribution

It extends the reproducing kernel approach to mean-field control, allowing representation of stochastic dynamics and nonlinear terminal costs without Pontryagin's principle.

Findings

Reproducing kernel Hilbert space characterizes mean-field control solutions.

Framework accommodates stochastic dynamics via conditional expectation.

Handles nonlinear terminal costs without adjoint processes.

Abstract

Mean-field control problems have received continuous interest over the last decade. Despite being more intricate than in classical optimal control, the linear-quadratic setting can still be tackled through Riccati equations. Remarkably, we demonstrate that another significant attribute extends to the mean-field case: the existence of an intrinsic reproducing kernel Hilbert space associated with the problem. Our findings reveal that this Hilbert space not only encompasses deterministic controlled push-forward mappings but can also represent of stochastic dynamics. Specifically, incorporating Brownian noise affects the deterministic kernel through a conditional expectation, to make the trajectories adapted. Introducing reproducing kernels allows us to rewrite the mean-field control problem as optimizing over a Hilbert space of trajectories rather than controls. This framework even accommodates nonlinear terminal costs, without resorting to adjoint processes or Pontryagin's maximum principle, further highlighting the versatility of the proposed methodology.