DocumentCode :
3587969
Title :
Game-theoretic learning in a distributed-information setting: Distributed convergence to mean-centric equilibria
Author :
Swenson, Brian ; Kar, Soummya ; Xavier, Joao
Author_Institution :
Dept. of Electr. & Comput. Eng., Carnegie Mellon Univ., Pittsburgh, PA, USA
fYear :
2014
Firstpage :
1616
Lastpage :
1620
Abstract :
The paper considers distributed learning in large-scale games via fictitious-play type algorithms. Given a preassigned communication graph structure for information exchange among the players, this paper studies a distributed implementation of the Empirical Centroid Fictitious Play (ECFP) algorithm that is well-suited to large-scale games in terms of complexity and memory requirements. It is shown that the distributed algorithm converges to an equilibrium set denoted as the mean-centric equilibria (MCE) for a reasonably large class of games.
Keywords :
computational complexity; distributed algorithms; game theory; graph theory; ECFP algorithm; MCE; complexity requirements; distributed algorithm; distributed learning; empirical centroid fictitious play algorithm; fictitious-play type algorithms; information exchange; large-scale games; mean-centric equilibria; memory requirements; preassigned communication graph structure; Cognition; Convergence; Economics; Games; History; Joints; Protocols;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Signals, Systems and Computers, 2014 48th Asilomar Conference on
Print_ISBN :
978-1-4799-8295-0
Type :
conf
DOI :
10.1109/ACSSC.2014.7094739
Filename :
7094739
Link To Document :
بازگشت