Optimistic robust linear quadratic dual control

by   Jack Umenberger, et al.

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.


page 1

page 2

page 3

page 4


Certainty Equivalent Control of LQR is Efficient

We study the performance of the certainty equivalent controller on the L...

On the Sample Complexity of the Linear Quadratic Regulator

This paper addresses the optimal control problem known as the Linear Qua...

Regret Bounds for Robust Adaptive Control of the Linear Quadratic Regulator

We consider adaptive control of the Linear Quadratic Regulator (LQR), wh...

Robust exploration in linear quadratic reinforcement learning

This paper concerns the problem of learning control policies for an unkn...

Robust Learning-Based Control via Bootstrapped Multiplicative Noise

Despite decades of research and recent progress in adaptive control and ...

Making Non-Stochastic Control (Almost) as Easy as Stochastic

Recent literature has made much progress in understanding online LQR: a ...

Convex Controller Synthesis for Contact

Controlling contacts is truly challenging, and this has been a major hur...