Unmanned aerial vehicle (UAV) swarm plays more and more important role in modern warfare, they can cooperate, communicate and share information with each other to enhance their survivability and combat ability in modern warfare. However, UAV swarm faces dynamic battlefield situation, making them hard to learning optimal cooperation and confrontation policy. To address the issues, a framework of UAV swarm cooperation and confrontation based on multi-agent deep reinforcement learning (MADRL) is proposed, and it can greatly improve training efficiency and model adaptability.
A Multi-agent Deep Reinforcement Learning Framework for UAV Swarm
Lect. Notes Electrical Eng.
Chinese Conference on Swarm Intelligence and Cooperative Control ; 2023 ; Nanjing, China November 24, 2023 - November 27, 2023
Proceedings of 2023 7th Chinese Conference on Swarm Intelligence and Cooperative Control ; Chapter : 36 ; 427-434
2024-06-15
8 pages
Article/Chapter (Book)
Electronic Resource
English
UAV Swarm Attack-Defense Confrontation Based on Multi-agent Reinforcement Learning
Springer Verlag | 2021
|Multi-Agent Deep Reinforcement Learning in Vehicular OCC
IEEE | 2022
|