Robustness of Stochastic Optimal Control to Approximate Diffusion Models under Several Cost Evaluation Criteria

TL;DR

This paper investigates the robustness of stochastic optimal control for diffusion processes, showing that errors due to model mismatch diminish as the approximate model converges to the true model, leveraging PDE regularity for strong results.

Contribution

It establishes the convergence of optimal values and control errors in continuous-time diffusion models under model approximation, extending robustness results beyond discrete-time settings.

Findings

Optimal value convergence under model approximation

Error due to control mismatch decreases with model accuracy

Utilizes PDE regularity for strong robustness properties

Abstract

In control theory, typically a nominal model is assumed based on which an optimal control is designed and then applied to an actual (true) system. This gives rise to the problem of performance loss due to the mismatch between the true model and the assumed model. A robustness problem in this context is to show that the error due to the mismatch between a true model and an assumed model decreases to zero as the assumed model approaches the true model. We study this problem when the state dynamics of the system are governed by controlled diffusion processes. In particular, we will discuss continuity and robustness properties of finite horizon and infinite-horizon $\alpha$-discounted/ergodic optimal control problems for a general class of non-degenerate controlled diffusion processes, as well as for optimal control up to an exit time. Under a general set of assumptions and a convergence criterion on the models, we first establish that the optimal value of the approximate model converges to the optimal value of the true model. We then establish that the error due to mismatch that occurs by application of a control policy, designed for an incorrectly estimated model, to a true model decreases to zero as the incorrect model approaches the true model. We will see that, compared to related results in the discrete-time setup, the continuous-time theory will let us utilize the strong regularity properties of solutions to optimality (HJB) equations, via the theory of uniformly elliptic PDEs, to arrive at strong continuity and robustness properties.