Dogfight Advantage Occupancy Method Based on Imperfect Information Self-Play

Air-to-air close combat is a typical combat scenario, which places extremely high physiological demands on pilots during the dogfight process. In order to achieve unmanned and intelligent close combat, this paper proposes a dogfight advantage occupancy algorithm based on imperfect information self-play. Through experiments on the high-fidelity F-16 aircraft platform, the results show that the algorithm can converge to a Nash equilibrium and fully utilize the maneuverability during the combat process.