Almost Surely $\sqrt{T}$ Regret for Adaptive LQR
This addresses a theoretical gap in control theory for adaptive systems, providing a near-optimal regret guarantee with practical safety mechanisms, though it is incremental in improving existing bounds.
The paper tackles the problem of achieving optimal regret bounds in adaptive Linear-Quadratic Regulation (LQR) with unknown parameters, and proposes a controller that achieves almost surely $ ilde{\mathcal{O}}(\sqrt{T})$ regret, validated via simulation on the Tennessee Eastman Process.
The Linear-Quadratic Regulation (LQR) problem with unknown system parameters has been widely studied, but it has remained unclear whether $\tilde{ \mathcal{O}}(\sqrt{T})$ regret, which is the best known dependence on time, can be achieved almost surely. In this paper, we propose an adaptive LQR controller with almost surely $\tilde{ \mathcal{O}}(\sqrt{T})$ regret upper bound. The controller features a circuit-breaking mechanism, which circumvents potential safety breach and guarantees the convergence of the system parameter estimate, but is shown to be triggered only finitely often and hence has negligible effect on the asymptotic performance of the controller. The proposed controller is also validated via simulation on Tennessee Eastman Process~(TEP), a commonly used industrial process example.