A Cooperative Jamming Decision-Making Method via Deep Reinforcement Learning

Cognitive electronic warfare is gaining increasing attention and will play an important role in warfare. Cognitive jamming decision making, as a key technology, significantly influences battlefield dynamics. Modern radar can work in multiple directions at the same time, and most of the existing research is on jamming style decision making of a single jammer, which is difficult to adapt to complex battlefield situations. Multiagent coordination can effectively deal with multifunctional radar, so this article investigates cooperative jamming decision-making algorithms. First, this article establishes a cooperative jamming decision-making model, in which three jammers are assumed to jam the radar in three directions and are based on a centralized learning distributed execution architecture. Then, this article extends the advantage actor–critic algorithm by proposing the multiagent advantage actor–critic (MA-A2C) algorithm and applying it to the model. In order to effectively solve the problems of high variance and environmental sensitivity in the MA-A2C algorithm, we propose two improvement methods and combine them to propose the multiagent heuristic dueling advantage actor–critic (MA-HDA2C) algorithm. We conducted simulation experiments on MA-A2C, two improved methods, and MA-HDA2C algorithms under the same modeling conditions. The results show that the MA-A2C algorithm can effectively carry out cooperative jamming decision making, but it has problems with low efficiency and poor stability. The MA-HDA2C algorithm has the advantages of fast convergence speed and stable convergence results. Compared with the MA-A2C algorithm, the MA-HDA2C algorithm has more significant superiority, which proves the effectiveness of the improvement method proposed in this article.