Mao-Long Lv

Addressing Hybrid Action of BVR Engagement With Joint Policy Optimization

Multiagent reinforcement learning (MARL) has attracted increasing attention in the context of beyond-visual-range engagements involving unmanned combat aerial vehicles (UCAVs) in recent years. UCAVs are required to make firing and maneuvering decisions simultaneously, while maneuvers also encompass both target-independ...