Global ETD Search

1	Playing is believing: the role of beliefs in multi-agent learning Chang, Yu-Han, Kaelbling, Leslie P. 01 1900 (has links) 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. / Singapore-MIT Alliance (SMA) multi-agent learning algorithm repeated games belief game theory Matrix games Nash equilibrium Stochastic games Reinforcement learning PHC-Exploiter