On the use of Markov Decision Processes in cognitive radar: An application to target tracking

In this paper we examine the radar-communications coexistence problem by modeling the radar environment as a Markov Decision Process (MDP), and then applying reinforcement learning to solve the optimization problem. The radar environment consists of a single moving target and a communications system that has to coexist with the radar. The communications system has several different modes: constant, intermittent, and triangular frequency sweep. We demonstrate how the MDP framework and reinforcement learning can be used to help the radar predict which bands the interferer will use and utilize bands that minimize interference, which in turn helps the radar optimize between range resolution and SINR.