Reinforcement Nash Equilibrium Solver

• المؤلفون الرئيسيون: WANG, Xinrun, YANG, Chang, LI, Shuxin, LI, Pengdeng, HUANG, Xiao, CHAN, Hau, AN, Bo
• التنسيق: text
• اللغة: English
• منشور في: Institutional Knowledge at Singapore Management University 2024
• الموضوعات: 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
• الوصول للمادة أونلاين: https://ink.library.smu.edu.sg/sis_research/9878; https://ink.library.smu.edu.sg/context/sis_research/article/10878/viewcontent/0030.pdf
• المؤسسة: 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...