Optimal Feedback for Stochastic Linear Quadratic Control and Backward Stochastic Riccati Equations in Infinite Dimensions

TL;DR

This paper addresses the longstanding challenge of characterizing optimal feedback controls for infinite-dimensional stochastic linear quadratic problems with random coefficients, linking it to backward stochastic Riccati equations.

Contribution

It establishes the equivalence between optimal feedback existence and Riccati equation solvability in infinite dimensions, introducing a new notion of transposition solutions.

Findings

Proves the existence of optimal feedback under verifiable assumptions.

Links feedback control problems to backward stochastic Riccati equations.

Introduces the concept of transposition solutions for Riccati equations.

Abstract

It is a longstanding unsolved problem to characterize the optimal feedbacks for general SLQs (i.e., stochastic linear quadratic control problems) with random coefficients in infinite dimensions; while the same problem but in finite dimensions was just addressed in a recent work [36]. This paper is devoted to giving a solution to this problem under some assumptions which can be verified for several interesting concrete models. More precisely, under these assumptions, we establish the equivalence between the existence of optimal feedback operator for infinite dimensional SLQs and the solvability of the corresponding operator-valued, backward stochastic Riccati equations. A key contribution of this work is to introduce a suitable notion of solutions (i.e., transposition solutions to the aforementioned Riccati equations), which plays a crucial role in both the statement and the proof of our main result.