Title :
Decentralized learning in two-player zero-sum games: A LR-I lagging anchor algorithm
Author :
Xiaosong Lu ; Schwartz, H.M.
Author_Institution :
Dept. of Syst. & Comput. Eng., Carleton Univ., Ottawa, ON, Canada
fDate :
June 29 2011-July 1 2011
Abstract :
This paper presents a LR-I lagging anchor algorithm that combines a lagging anchor method to the LR-I learning algorithm. We prove that this decentralized learning algorithm converges in strategies to a Nash equilibrium in two-player, zero-sum, two-action matrix games, while only needing knowledge of their own action and reward.
Keywords :
game theory; learning (artificial intelligence); matrix algebra; multi-agent systems; LR-I lagging anchor algorithm; LR-I learning algorithm; Nash equilibrium; decentralized learning algorithm; lagging anchor method; two-player zero-sum two-action matrix games; Algorithm design and analysis; Convergence; Games; Learning automata; Nash equilibrium;
Conference_Titel :
American Control Conference (ACC), 2011
Conference_Location :
San Francisco, CA
Print_ISBN :
978-1-4577-0080-4
DOI :
10.1109/ACC.2011.5990832
