作战方案驱动的可学习兵棋推演智能体研究
Research on Learnable Wargame Agent Driven by Battle Scheme
孙怡峰 1李智 1吴疆 1王玉宾2
作者信息
- 1. 战略支援部队信息工程大学,河南郑州 450001
- 2. 中国人民解放军66389部队,河南郑州 450000
- 折叠
摘要
为了使智能体能够应对兵棋推演中的复杂作战场景和作战目的,提出作战方案驱动的可学习兵棋推演智能体架构.剖析智能体对兵棋系统的"依附特性"和"松耦合特性",得到智能体的可学习要求;在智能体框架设计中,使用作战方案压减智能体学习范围.通过有限状态机对应作战方案中的作战阶段知识,依据作战方案框架确定智能体决策空间,设计可学习的深层神经网络实施关键决策空间探索,神经网络采用先验知识模仿学习模式和深度强化学习模式.该架构能迭代探索人类难以充分梳理清楚的多棋子最优部署和协作问题.
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.
关键词
兵棋推演/智能体/作战方案/深层神经网络/强化学习/模仿学习Key words
wargame/agent/battle scheme/deep neural network/reinforcement learning/imitation learning引用本文复制引用
出版年
2024
NETL
NSTL
万方数据