Playing is believing: the role of beliefs in multi-agent learning
Author(s)Chang, Yu-Han; Kaelbling, Leslie P.
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.
Computer Science (CS);
multi-agent learning algorithm, repeated games, belief, game theory, Matrix games, Nash equilibrium, Stochastic games, Reinforcement learning, PHC-Exploiter