Reinforcement Nash Equilibrium Solver

• Main Authors: WANG, Xinrun, YANG, Chang, LI, Shuxin, LI, Pengdeng, HUANG, Xiao, CHAN, Hau, AN, Bo
• Format: text
• Language: English
• Published: Institutional Knowledge at Singapore Management University 2024
• Subjects: Nash equilibrium; game theory; reinforcement learning; REinforcement Nash Equilibrium Solver (RENES); graph neural networks; tensor decomposition; proximal policy optimization; α-rank; correlated equilibrium; fictitious play; Artificial Intelligence and Robotics
• Online Access: https://ink.library.smu.edu.sg/sis_research/9878; https://ink.library.smu.edu.sg/context/sis_research/article/10878/viewcontent/0030.pdf
• Institution: Singapore Management University

Nash Equilibrium (NE) is the canonical solution concept of game theory, which provides an elegant tool to understand the rationalities. Though mixed strategy NE exists in any game with finite players and actions, computing NE in two- or multi-player general-sum games is PPAD-Complete. Various altern...