智能科学与技术学报 ›› 2022, Vol. 4 ›› Issue (2): 157-173.doi: 10.11959/j.issn.2096-6652.202209

• 综述与展望 • 上一篇    下一篇

智能博弈综述:游戏AI对作战推演的启示

孙宇祥1, 彭益辉1, 李斌1, 周佳炜1, 张鑫磊1, 周献中1,2   

  1. 1 南京大学工程管理学院,江苏 南京 210093
    2 南京大学智能装备新技术研究中心,江苏 南京 210093
  • 出版日期:2022-06-15 发布日期:2022-06-01
  • 作者简介:孙宇祥(1990− ),男,南京大学工程管理学院博士生,主要研究方向为智能博弈与作战推演
    彭益辉(1995− ),男,南京大学工程管理学院硕士生,主要研究方向为多智能体深度强化学习技术
    李斌(1998− ),男,南京大学工程管理学院硕士生,主要研究方向为分层强化学习及智能博弈
    周佳炜(1997−),男,南京大学工程管理学院硕士生,主要研究方向为深度强化学习算法设计
    张鑫磊(1996− ),男,南京大学工程管理学院硕士生,主要研究方向为智能体多通道人机交互及智能博弈
    周献中(1962− )男,博士,南京大学工程管理学院教授,主要研究方向为混合智能系统协作与任务规划、指挥与控制系统理论与技术等
  • 基金资助:
    国家自然科学基金资助项目(61876079)

Overview of intelligent game:enlightenment of game AI to combat deduction

Yuxiang SUN1, Yihui PENG1, Bin LI1, Jiawei ZHOU1, Xinlei ZHANG1, Xianzhong ZHOU1,2   

  1. 1 School of Management and Engineering, Nanjing University, Nanjing 210093, China
    2 Research Center for New Technology in Intelligent Equipment Nanjing University, Nanjing 210093, China
  • Online:2022-06-15 Published:2022-06-01
  • Supported by:
    The National Natural Science Foundation of China(61876079)

摘要:

智能博弈领域已逐渐成为当前AI研究的热点之一,游戏AI领域、智能兵棋领域都在近年取得了一系列的研究突破。但是,游戏 AI 如何应用到实际的智能作战推演依然面临巨大的困难。综合分析智能博弈领域的国内外整体研究进展,详细剖析智能作战推演的主要属性需求,并结合当前最新的强化学习发展概况进行阐述。从智能博弈领域主流研究技术、相关智能决策技术、作战推演技术难点3个维度综合分析游戏AI发展为智能作战推演的可行性,最后给出未来智能作战推演的发展建议。以期为智能博弈领域的研究人员介绍一个比较清晰的发展现状并提供有价值的研究思路。

关键词: 智能博弈, 游戏AI, 智能作战推演, 智能兵棋, 深度强化学习

Abstract:

The field of intelligent game has gradually become one of the hotspots of AI research.A series of research breakthroughs have been made in the field of game AI and intelligent wargame in recent years.However, how to develop game AI and apply it to the actual intelligent combat deduction is still facing great difficulties.The overall progress of research in the field of intelligent games in domestic and overseas were explored, the main attribute requirements of intelligent combat deduction was tracked, and it was summarized with the latest advancements in reinforcement learning.The feasibility of developing game AI into intelligent combat deduction were comprehensively analyzed from three dimensions: mainstream research technology in the field of intelligent game, relevant intelligent decision technology and technical difficulties of combat deduction, and finally, some suggestions for the development of future intelligent combat deductiongives were given.This paper can introduce a clear development status and provide valuable research ideas for researchers in the field of intelligent game.

Key words: intelligent game, game AI, intelligent combat deduction, intelligent wargame, deep reinforcement learning

中图分类号: 

No Suggested Reading articles found!