Current research on cooperative jamming against radar networks primarily focuses on static optimization problems, such as localization error compensation and electromagnetic resource allocation, while largely neglecting the dynamic trajectory planning of UAV swarms. To address this gap, this paper proposes a cooperative control algorithm for UAVs based on deep reinforcement learning (DRL). First, we establish a jamming model for radar networks. Then, we present a DRL-based cooperative UAV trajectory planning method for radar network jamming, introducing the first multi-step optimization approach for jamming trajectory planning. Finally, simulation results demonstrate that the proposed method outperforms conventional one-step optimization approaches, enabling intelligent cooperative jamming against radar networks.