指挥控制与仿真2024，Vol.46Issue(3)：62-69,8.DOI:10.3969/j.issn.1673-3819.2024.03.010
基于深度强化学习算法的火力-目标分配方法
Firepower-target assignment method based on deep reinforcement learning algorithm
李伟光 1陈栋1
作者信息
- 1. 陆军炮兵防空兵学院高过载弹药制导控制与信息感知实验室,安徽 合肥 230031
- 折叠
摘要
Abstract
Aiming at the characteristics of large solution space,discrete,dynamic and nonlinear of firepower-target assign-ment problem,this paper proposes a deep reinforcement learning algorithm based on DQN.By combining the 6-layer fully connected feedforward neural network with the Q-learning algorithm,the perception ability of deep learning and the decision-making ability of reinforcement learning are fully utilized.Through the comparison of model performance tests,this method has strong fitting ability,fast convergence speed and small variance jitter,and the distribution results meet the combat ex-pectations,which can provide some reference for commanders to make decisions on fire strike problems.关键词
火力-目标分配/深度强化学习/Q-learning算法/DQN算法Key words
firepower-target assignment/deep reinforcement learning/Q-learning algorithm/DQN algorithm分类
军事科技引用本文复制引用
李伟光,陈栋..基于深度强化学习算法的火力-目标分配方法[J].指挥控制与仿真,2024,46(3):62-69,8.
