Research on Learnable Wargame Agent Driven by Battle Scheme

Authors

Yifeng Sun, Strategic Support Force Information Engineering University, Zhengzhou 450001, ChinaFollow
Zhi Li, Strategic Support Force Information Engineering University, Zhengzhou 450001, China;
Jiang Wu, Strategic Support Force Information Engineering University, Zhengzhou 450001, China;
Yubin Wang, PLA 66389 Troops, Zhengzhou 450000, China

Abstract

Abstract: To enable the agent to cope with complex battle scenarios and objectives in wargame, a learnable wargame agent architecture driven by a battle scheme is proposed. By analyzing the "attachment characteristics" and "loose coupling characteristics" of the agent to wargame system, the learnable requirements of the agent are obtained. In the design of the agent framework, battle schemes are used to reduce the learning range of the agent. The finite state machine corresponds to the knowledge of the operational phase in the battle scheme, and the decision-making space of the agent is determined according to the framework of the battle scheme. A learnable deep neural network is designed to explore key decision space. The neural network uses prior knowledge imitation learning mode and deep reinforcement learning mode. This architecture can iteratively explore optimal deployment and collaboration issues for multiple chessmen that are difficult for humans to fully tease out.

Recommended Citation

Sun, Yifeng; Li, Zhi; Wu, Jiang; and Wang, Yubin (2024) "Research on Learnable Wargame Agent Driven by Battle Scheme," Journal of System Simulation: Vol. 36: Iss. 7, Article 2.
DOI: 10.16182/j.issn1004731x.joss.23-0477
Available at: https://dc-china-simulation.researchcommons.org/journal/vol36/iss7/2

First Page

1525

Last Page

1535

CLC

TP391.9

Recommended Citation

Sun Yifeng, Li Zhi, Wu Jiang, et al. Research on Learnable Wargame Agent Driven by Battle Scheme [J]. Journal of System Simulation, 2024, 36(7): 1525-1535.

DOI

10.16182/j.issn1004731x.joss.23-0477