Pith. sign in

Learning Linear-Quadratic Regulators Efficiently with only $\sqrt{T}$ Regret

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it
abstract

We present the first computationally-efficient algorithm with $\widetilde O(\sqrt{T})$ regret for learning in Linear Quadratic Control systems with unknown dynamics. By that, we resolve an open question of Abbasi-Yadkori and Szepesv\'ari (2011) and Dean, Mania, Matni, Recht, and Tu (2018).

fields

eess.SY 1

years

2026 1

verdicts

CONDITIONAL 1

representative citing papers

Regret-Guaranteed Safe Switching: LQR Setting with Unknown Dynamics

eess.SY · 2026-06-20 · conditional · novelty 7.0

An SDP-based algorithm estimates both control gains and minimum dwell times online for switched LQR systems with unknown dynamics, achieving O(|M|^{1/4} n_s^{3/4} + n_m) expected regret while keeping state norms bounded.

citing papers explorer

Showing 1 of 1 citing paper.

  • Regret-Guaranteed Safe Switching: LQR Setting with Unknown Dynamics eess.SY · 2026-06-20 · conditional · none · ref 15 · internal anchor

    An SDP-based algorithm estimates both control gains and minimum dwell times online for switched LQR systems with unknown dynamics, achieving O(|M|^{1/4} n_s^{3/4} + n_m) expected regret while keeping state norms bounded.