混合博弈问题的求解与应用综述
作者:
作者单位:

作者简介:

通讯作者:

中图分类号:

TP18

基金项目:

国家自然科学基金(62192783, 62106100, 62206133, 62276142); 江苏省自然科学基金(BK20221441); 江苏省产业前瞻与关键核心技术竞争项目(BE2021028); 深圳市中央引导地方科技发展资金(2021Szvup056); 南京大学计算机软件新技术国家重点实验室资助项目(KFKT2022B12)


Survey on Solutions and Applications for Mixed-motive Games
Author:
Affiliation:

Fund Project:

  • 摘要
  • |
  • 图/表
  • |
  • 访问统计
  • |
  • 参考文献
  • |
  • 相似文献
  • |
  • 引证文献
  • |
  • 资源附件
  • |
  • 文章评论
    摘要:

    近年来, 随着人工智能技术在序贯决策和博弈对抗等问题的应用方面取得了飞速发展, 围棋、游戏、德扑和麻将等领域取得了巨大的进步, 例如, AlphaGo、OpenAI Five、AlphaStar、DeepStack、Libratus、Pluribus和Suphx等系统都在这些领域中达到或超过人类专家水平. 这些应用集中在双人、两队或者多人的零和博弈问题中, 而对于混合博弈问题的研究缺乏实质性的进展与突破. 区别于零和博弈, 混合博弈需要综合考虑个体收益、集体收益和均衡收益等诸多目标, 被广泛应用于公共资源分配、任务调度和自动驾驶等现实场景. 因此, 对于混合博弈问题的研究至关重要. 本文通过梳理当前混合博弈领域中的重要概念和相关工作, 深入分析国内外研究现状和未来发展方向. 具体地, 本文首先介绍混合博弈问题的定义与分类; 其次详细阐述博弈解概念和求解目标, 包含纳什均衡、相关均衡、帕累托最优等解概念, 最大化个体收益、最大化集体收益以及兼顾公平等求解目标; 接下来根据不同的求解目标, 分别对博弈论方法、强化学习方法以及这两种方法的结合进行详细地探讨和分析; 最后介绍相关的应用场景和实验仿真环境, 并对未来研究的方向进行总结与展望.

    Abstract:

    In recent years, there has been rapid advancement in the application of artificial intelligence technology to sequential decision-making and adversarial game scenarios, resulting in significant progress in domains such as Go, various games, poker, and Mahjong. Notably, systems like AlphaGo, OpenAI Five, AlphaStar, DeepStack, Libratus, Pluribus, and Suphx have achieved or surpassed human expert-level performance in these areas. While these applications primarily focus on zero-sum games involving two players, two teams, or multiple players, there has been limited substantive progress in addressing mixed-motive games. Unlike zero-sum games, mixed-motive games necessitate comprehensive consideration of individual gains, collective gains, and equilibrium. These games are extensively applied in real-world contexts such as public resource allocation, task scheduling, and autonomous driving, making research in this area crucial. This paper offers a comprehensive overview of key concepts and relevant research in the field of mixed-motive games, providing an in-depth analysis of current trends and future directions both domestically and internationally. Specifically, this study first introduces the definition and classification of mixed-motive games. It then elaborates on game solution concepts and objectives, including Nash equilibrium, correlated equilibrium, and Pareto optimality, as well as objectives related to maximizing individual and collective gains, while considering fairness. Furthermore, the study engages in a thorough exploration and analysis of game theory methods, reinforcement learning methods, and their combination based on different solution objectives. In addition, the paper discusses relevant application scenarios and experimental simulation environments before concluding with a summary and outlook on future research directions.

    参考文献
    相似文献
    引证文献
引用本文

董绍康,李超,杨光,葛振兴,曹宏业,陈武兵,杨尚东,陈兴国,李文斌,高阳.混合博弈问题的求解与应用综述.软件学报,,():1-47

复制
分享
文章指标
  • 点击次数:
  • 下载次数:
  • HTML阅读次数:
  • 引用次数:
历史
  • 收稿日期:2023-08-03
  • 最后修改日期:2024-01-14
  • 录用日期:
  • 在线发布日期: 2024-06-20
  • 出版日期:
您是第位访问者
版权所有:中国科学院软件研究所 京ICP备05046678号-3
地址:北京市海淀区中关村南四街4号,邮政编码:100190
电话:010-62562563 传真:010-62562533 Email:jos@iscas.ac.cn
技术支持:北京勤云科技发展有限公司

京公网安备 11040202500063号