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

We consider the problem of designing a control law for a constrained linear system with bounded disturbances that ensures constraint satisfaction over an infinite horizon, while also guaranteeing that the closed-loop system has bounded gain. To this end, we propose a receding horizon control strategy based on the repeated calculation of optimal finite horizon feedback policies. We parameterize ...

In this paper, we propose a uni ed mathematical framework based on receding horizon control for analyzing and designing AQM (Active Queue Management) algorithms in stabilizing a given TCP (Transfer Control Protocol) algorithm. The proposed framework is based on a dynamical system of the given TCP and minimization of a linear quadratic cost on the transients in queue length, aggregate rate, jitt...

A typical bottleneck of model predictive control algorithms is the computational burden in order to compute the receding horizon feedback law which is predominantly determined by the length of the prediction horizon. Based on a relaxed Lyapunov inequality we present techniques which allow us to show stability and suboptimality estimates for a reduced prediction horizon. In particular, the known...

The problem of constrained model predictive control on a class of stochastic linear parameter varying systems is discussed. First, constant coefficient matrices are obtained at each vertex in the interior of system, and then, by considering semi-definite programming constraints, weight coefficients between each vertex are calculated, and the equal coefficient matrices for the time variant syste...