Multi-agent air combat simulation based on NetLogo

Computer simulation is a crucial approach for advancing research in intelligent aerial combat. However, existing aerial combat simulators are often non-open-source, challenging to develop, poorly visualized, and difficult to integrate with advanced AI technologies. This paper introduces a 3D aerial combat simulation system based on NetLogo 3D and HubNet. The system constructs static models of terrain, aircraft, and missiles in NetLogo 3D, and encapsulates functions to implement dynamic behaviors such as aircraft maneuvers and missile attacks. The system not only supports expert algorithms but also integrates DDQN reinforcement learning algorithm via Python extensions, enabling intelligent agents to make maneuver and attack decisions. A C-S architecture is employed via HubNet to support various simulation scenarios, including human-human, human-machine, and machine-machine engagements. Experimental results validate the system's effectiveness and stability, highlighting its real-time visualization capabilities and rapid integration of AI algorithms.