Playing is believing: the role of beliefs in multi-agent learning
Author(s)
Chang, Yu-Han
Kaelbling, Leslie P.
Date Issued
January 2003
Series/Report no.
Computer Science (CS);
Abstract
We propose a new classification for multi-agent learning algorithms, with each league of players characterized by both their possible strategies and possible beliefs. Using this classification, we review the optimality of existing algorithms and discuss some insights that can be gained. We propose an incremental improvement to the existing algorithms that seems to achieve average payoffs that are at least the Nash equilibrium payoffs in the long-run against fair opponents.
Subjects
multi-agent learning algorithm
repeated games
belief
game theory
Matrix games
Nash equilibrium
Stochastic games
Reinforcement learning
PHC-Exploiter
Persistent DSpace Link
