Robust Policy Iteration for Continuous-Time Linear Quadratic Regulation

This article studies the robustness of policy iteration in context continuous-time infinite-horizon linear quadratic regulator (LQR) problem. It is shown that Kleinman's algorithm small-disturbance input-to-state stable, a property stronger than Sontag's local stability but weaker global stability. More precisely, whenever error each bounded and small, solutions are also enter small neighborhood optimal solution LQR Based on this result, an off-policy data-driven for problem to be robust when system dynamics subject additive unknown disturbances. The theoretical results validated by numerical example.