An Improved Method Based on Q-Learning for Jamming Strategy Optimization

With the increasing sophistication of radar systems, jamming countermeasures have become more complex and variable. To effectively respond to complex and unknown threat signals, there is a need to enhance the intelligent capabilities of countermeasure systems. This paper proposes an intelligent optimization method for jamming strategies based on an improved Q-Learning algorithm. Through simulation experiments, we study the countermeasure strategies for ground-based phased array radars. Experimental results show that the improved Q-Learning algorithm can obtain the optimal allocation of jamming strategies with fewer iterations, improving countermeasure performance and preliminarily demonstrating the feasibility of this approach.