CFR-MIX: Solving imperfect information extensive-form games with combinatorial action space

• Main Authors: LI, Shuxin, ZHANG, Youzhi, WANG, Xinrun, XUE, Wanqi, AN, Bo
• Format: text
• Language: English
• Published: Institutional Knowledge at Singapore Management University 2021
• Subjects: Security and privacy; noncooperative games; Computational sustainability; Artificial Intelligence and Robotics; Theory and Algorithms
• Online Access: https://ink.library.smu.edu.sg/sis_research/9138; https://ink.library.smu.edu.sg/context/sis_research/article/10141/viewcontent/CFR_MIX_pvoa.pdf
• Institution: Singapore Management University

In many real-world scenarios, a team of agents must coordinate with each other to compete against an opponent. The challenge of solving this type of game is that the team's joint action space grows exponentially with the number of agents, which results in the inefficiency of the existing algori...