Learning in Stochastic Games: A Review of the Literature

A great deal of research has been recently focused on stochastic games. Stochastic games can generally model the interactions between multiple agents in an environment. One of the major challenges in stochastic games is the problem of learning a policy to play in such games. While lots of people have worked in this area and proposed various algorithms for that, there is no unique method which can outperform all other methods. Therefore, one should know the pros and cons of different algorithms in the literature to select the one that suits his/her situation best. In this paper, we survey different methods proposed in the literature, group them according to their approaches and discuss about the general advantages and disadvantages of each group.