文献类型：期刊文献

英文题名：Cooperative and Competitive Multi-Agent Systems: From Optimization to Games

作者：Wang, Jianrui[1];Hong, Yitian[1];Wang, Jiali[1];Xu, Jiapeng[2];Tang, Yang[1];Han, Qing-Long[3];Kurths, Jurgen[4,5]

机构：[1]East China Univ Sci & Technol, Key Lab Smart Mfg Energy Chem Proc, Minist Educ, Shanghai 200237, Peoples R China;[2]Univ Windsor, Dept Elect & Comp Engn, Windsor, ON N9B 3P4, Canada;[3]Swinburne Univ Technol, Sch Sci Comp & Engn Technol, Melbourne, Vic 3122, Australia;[4]Potsdam Inst Climate Impact Res, D-14473 Potsdam, Germany;[5]Humboldt Univ, Inst Phys, D-12489 Berlin, Germany

年份：2022

卷号：9

期号：5

起止页码：763

外文期刊名：IEEE-CAA JOURNAL OF AUTOMATICA SINICA

收录：;EI(收录号：20221912095262);WOS:【SSCI(收录号:WOS:000794202700006)，SCI-EXPANDED(收录号:WOS:000794202700006)】；

基金：This work was supported in part by the National Natural Science Foundation of China (Basic Science Center Program: 61988101), the Sino-German Center for Research Promotion (M-0066), the International (Regional) Cooperation and Exchange Project (61720106008), the Programme of Introducing Talents of Discipline to Universities (the 111 Project) (B17017), and the Program of Shanghai Academic Research Leader (20XD1401300). Recommended by Associate Editor Tao Yang. (Jianrui Wang and Yitian Hong contributed equally to this work. Corresponding author: Yang Tang and Qing-Long Han.)

语种：英文

外文关键词：Cooperative games; counterfactual regret minimization; distributed optimization; federated optimization; fictitious self-play; mean field games; multi-agent reinforcement learning; non-cooperative games

摘要：Multi-agent systems can solve scientific issues related to complex systems that are difficult or impossible for a single agent to solve through mutual collaboration and cooperation optimization. In a multi-agent system, agents with a certain degree of autonomy generate complex interactions due to the correlation and coordination, which is manifested as cooperative/competitive behavior. This survey focuses on multi-agent cooperative optimization and cooperative/non-cooperative games. Starting from cooperative optimization, the studies on distributed optimization and federated optimization are summarized. The survey mainly focuses on distributed online optimization and its application in privacy protection, and overviews federated optimization from the perspective of privacy protection mechanisms. Then, cooperative games and non-cooperative games are introduced to expand the cooperative optimization problems from two aspects of minimizing global costs and minimizing individual costs, respectively. Multi-agent cooperative and non-cooperative behaviors are modeled by games from both static and dynamic aspects, according to whether each player can make decisions based on the information of other players. Finally, future directions for cooperative optimization, cooperative/non-cooperative games, and their applications are discussed.