MetaTOC stay on top of your field, easily

Reinforcement Q-learning optimal control of 2D discrete-time systems with unknown dynamics

, , , , ,

Transactions of the Institute of Measurement and Control

Published online on

Abstract

Transactions of the Institute of Measurement and Control, Ahead of Print.
This paper proposes a Q-learning-based algorithm to solve the linear quadratic regulator (LQR) problem for unknown dynamic two-dimensional (2D) discrete-time systems. First, based on the value function formulation constructed using the Lyapunov function ...