Multi-agent multi-dimensional joint optimisation of jamming decision-making against multi-functional radar

Abstract

The authors propose a multi-agent, multi-dimensional joint optimisation decision-making strategy to tackle the challenges jammers encounter when interfering with multi-functional radars, which possess advanced anti-interference capabilities. The strategy is divided into optimising the interference style and three parameters: timing, power, and duration, to enhance interference effectiveness. Furthermore, state value reuse is combined with the duelling double deep Q-learning and multi-agent deep deterministic policy gradient algorithms to effectively manage the multi-dimensional optimisation of the interference strategy. Simulation results demonstrate that the proposed algorithm outperforms Ant-QL, heuristic accelerated Q-learning, and asynchronous advantage actor-critic algorithms in terms of convergence speed and stability. It identifies a more efficient strategy for transitioning the radar from its initial state to the state with the lowest threat level to the jammer, achieving a 24% improvement in convergence speed. Additionally, the performance curve exhibits better stability.