chapter
Introduction to Learning in Games
ByHamidou Tembine
Pages 51

One of the objectives in distributed interacting multi-player systems is to enable a collection of selfish players to achieve a desirable objective. There are two overriding challenges to achieving this objective. The first one is related to the complexity of finding the optimal solution. A centralized algorithm may be prohibitively complex when there are a large number of interacting players. This motivates the use of adaptive methods that enable players to self-organize into suitable, if not optimal, alternative solutions. The second challenge is limited information. Players may have limited knowledge about the status of other players, except perhaps for a small subset of neighboring players. The limitations in terms of information induce robust stochastic optimization, bounded rationality and inconsistent beliefs. As a consequence, there are many simple games in which the beliefs may converge but not the strategies. The outcome is sensitive to

how much signalling is available to the players,

the nature of the learning scheme,

the way the information is exploited.

Common Knowledge