Research on autonomous decision-making method of beyond visual range air combat based on deep reinforcement learning and self-game

Modern beyond visual range (BVR) air combat has become the main form of air combat, and it requires fighters to make optimal decisions quickly in a complex environment to ensure an advantage in confrontation. In this paper, an intelligent decision-making algorithm based on Deep Q-network (DQN) and self-game is proposed to solve the maneuvering decision-making problem in BVR air combat, and the priority opponent sampling mechanism is introduced to improve the diversity and generalization ability of the strategy. The experimental results show that the proposed method can better accumulate rewards and achieve convergence in the training process, and show stronger maneuverability and confrontation ability. The research results show that the proposed method can effectively improve the decision-making performance of agents in complex confrontation environment.