Revisiting LQR Control from the Perspective of Receding-Horizon Policy Gradient

We revisit in this paper the discrete-time linear quadratic regulator (LQR) problem from the perspective of receding-horizon policy gradient (RHPG), a newly developed model-free learning framework for control applications. We provide a fine-grained sample complexity analysis for RHPG to learn a control policy that is both stabilizing and $\epsilon$-close to the optimal LQR solution, and our algorithm does not require knowing a stabilizing control policy for initialization. Combined with the recent application of RHPG in learning the Kalman filter, we …

analysis applications complexity control cs.ai cs.lg cs.sy eess.sy fine-grained framework free gradient horizon learn linear math.oc paper perspective policy regulator sample