Optimistic robust linear quadratic dual control

Abstract

Recent work by Mania et al. has proved that certainty equivalent control achieves nearly optimal regret for linear systems with quadratic costs. However, when parameter uncertainty is large, certainty equivalence cannot be relied upon to stabilize the true, unknown system. In this paper, we present a dual control strategy that attempts to combine the performance of certainty equivalence, with the practical utility of robustness. The formulation preserves structure in the representation of parametric uncertainty, which allows the controller to target reduction of uncertainty in the parameters that `matter most' for the control task, while robustly stabilizing the uncertain system. Control synthesis proceeds via convex optimization, and the method is illustrated on a numerical example.

Preprint submitted to L4DC 2020. 11 pages. 1 figure

References in corpus (8)

• Logarithmic Regret for Online Control
• Learning-based Control of Unknown Linear Systems with Thompson Sampling
• Thompson Sampling for Linear-Quadratic Control Problems
• Online Linear Quadratic Control
• From self-tuning regulators to reinforcement learning and back again
• Learning convex bounds for linear quadratic control policy synthesis
• Robust exploration in linear quadratic reinforcement learning
• Robust Closed-loop Model Predictive Control via System Level Synthesis