指挥控制与仿真2024，Vol.46Issue(2)：35-43,9.DOI:10.3969/j.issn.1673-3819.2024.02.006
海空跨域协同兵棋AI架构设计及关键技术分析
Architecture design and key technologies analysis of wargaming AI for sea-air cross-domain coordination
摘要
Abstract
The breakthrough and progress of intelligent gaming technology with deep reinforcement learning as the core in the field of games provide a method reference for the research of agents in sea-air wargames.The architecture design of the a-gent is the primary core key problem that needs to be solved,and a good architecture can reduce the complexity and difficulty of training and accelerate the convergence of policies.A stochastic game model of sea-air cross-domain cooperative decision-making has been proposed,and its corresponding equilibrium solution concepts have been analyzed.Based on the analysis of typical agent frameworks,aiming at the decision-making gaming process of sea-air wargames,and then an agent bi-level ar-chitecture based on multi-Agent hierarchical reinforcement learning is proposed,which can effectively solve the problems of collaboration and dimensional disaster.The key technologies are analyzed from four aspects:force coordination,agent net-work design,adversary modeling and training mechanism.Hoping to provide architectural guidance for the subsequent design and implementation of sea-air wargaming agents.关键词
海空兵棋/跨域协同/兵棋推演/多智能体/智能博弈/模型架构/分层强化学习Key words
sea-air wargame/cross-domain cooperation/wargaming/multi-agent/intelligent gaming/model architecture/hierarchical reinforcement learning分类
军事科技引用本文复制引用
苏炯铭,罗俊仁,陈少飞,项凤涛..海空跨域协同兵棋AI架构设计及关键技术分析[J].指挥控制与仿真,2024,46(2):35-43,9.基金项目
国家自然科学基金(61806212、62376280) （61806212、62376280）
