系统仿真学报 ›› 2025, Vol. 37 ›› Issue (3): 763-774.doi: 10.16182/j.issn1004731x.joss.23-1397

• 论文 • 上一篇    

基于强化学习的导弹突防决策建模研究

张斌1, 雷永林2, 李群2, 高远2, 陈永2, 朱佳俊2, 鲍琛龙1   

  1. 1.国防科技大学 计算机学院,湖南 长沙 410073
    2.国防科技大学 系统工程学院,湖南 长沙 410073
  • 收稿日期:2023-11-17 修回日期:2024-01-08 出版日期:2025-03-17 发布日期:2025-03-21
  • 通讯作者: 雷永林
  • 第一作者简介:张斌(1976-),男,研究员,博士,研究方向为装备知识工程。

Reinforcement Learning Modeling of Missile Penetration Decision Based on Combat Simulation

Zhang Bin1, Lei Yonglin2, Li Qun2, Gao Yuan2, Chen Yong2, Zhu Jiajun2, Bao Chenlong1   

  1. 1.College of College of Computer Science and Technology, National University of Defense Technology, Changsha 410073, China
    2.College of Systems Engineering, National University of Defense Technology, Changsha 410073, China
  • Received:2023-11-17 Revised:2024-01-08 Online:2025-03-17 Published:2025-03-21
  • Contact: Lei Yonglin

摘要:

突防能力是导弹等装备的关键评价指标,针对传统基于知识工程的突防决策方法难以自适应演进的不足,提出了基于作战仿真和深度强化学习结合的智能突防决策建模方法。搭建了基于WESS的导弹智能决策训练环境;以导弹机动突防决策建模为例进行了应用研究,建立了机动突防决策网络模型基于离散SAC算法进行了决策模型的强化学习训练,并开展智能化测试对比。初步试验结果表明:基于机器学习的智能决策模型具有更好的突防效果。

关键词: 导弹突防, 智能决策, 深度强化学习, 作战仿真, WESS仿真系统

Abstract:

Penetration capability is a primary measure of missile systems. In response to the shortcomings of traditional knowledge-based decision-making methods that are difficult to adaptively evolve, an intelligent penetration decision-making based on combat simulation and DRL is proposed. A missile intelligent decision-making training environment is constructed based on the WESS system. Taking missile maneuver penetration decision-making as an example, a maneuver penetration decision-making network model is designed and trained based on the SAC-discrete algorithm and the test of intelligence is conducted. Experimental results show that the intelligent decision model derived from machine learning has a better combat outcome than traditional methods.

Key words: missile penetration, intelligent decision-making, DRL, combat simulation, WESS simulation system

中图分类号: