Deep reinforcement learning based missile guidance law design for maneuvering target interception

In this paper, a novel guidance law based on deep reinforcement learning (DRL) algorithm is presented to deal with the maneuvering target interception problem. First, a missile target interception environment model under the framework of DRL is constructed. Then we designed a reward function based on miss distance and constructed an agent based on deep deterministic policy gradient (DDPG) for training. Finally, simulation results illustrate the effectiveness and excellent performance of the proposed method.