Multi-UCAV Air Combat in Short-Range Maneuver Strategy Generation using Reinforcement Learning and Curriculum Learning

Weiren Kong, Deyun Zhou, Kai Zhang, Zhen Yang, Wansha Yang

科研成果: 书/报告/会议事项章节会议稿件同行评审

10 引用 (Scopus)

摘要

We present an approach for learning a reactive maneuver strategy for a UCAV formation involved in a short-range multi-UCAV air combat engagement. Specifically, we define an efficient state representation, which breaks down the complexity caused by the large state space in a multi-UCAV air combat engagement. Then a parameter sharing dueling deep Q-network (PS-DDQN) algorithm is proposed to train the UCAV formation. The learning reactive maneuver strategy is shared among our UCAVs to encourage cooperative behaviors. In addition, curriculum learning and self-play extend the maneuver strategy to more difficult scenarios. Thus, speeding up the training process and improving the learning effect. Finally, the effectiveness of the algorithm and the intelligence degree of maneuver strategy is verified by the simulation test of convergence and maneuver strategy quality.

源语言英语
主期刊名Proceedings - 19th IEEE International Conference on Machine Learning and Applications, ICMLA 2020
编辑M. Arif Wani, Feng Luo, Xiaolin Li, Dejing Dou, Francesco Bonchi
出版商Institute of Electrical and Electronics Engineers Inc.
1174-1181
页数8
ISBN(电子版)9781728184708
DOI
出版状态已出版 - 12月 2020
活动19th IEEE International Conference on Machine Learning and Applications, ICMLA 2020 - Virtual, Miami, 美国
期限: 14 12月 202017 12月 2020

出版系列

姓名Proceedings - 19th IEEE International Conference on Machine Learning and Applications, ICMLA 2020

会议

会议19th IEEE International Conference on Machine Learning and Applications, ICMLA 2020
国家/地区美国
Virtual, Miami
时期14/12/2017/12/20

指纹

探究 'Multi-UCAV Air Combat in Short-Range Maneuver Strategy Generation using Reinforcement Learning and Curriculum Learning' 的科研主题。它们共同构成独一无二的指纹。

引用此