This paper studies the analytical properties of the reinforcement learning model proposed in Erev and Roth (1998), also termed cumulative reinforcement learning in Laslier et al. (2001).

It is known (see, e.g., Weibull in Evolutionary Game Theory, MIT Press, <CitationRef CitationID="CR7">1995</CitationRef>) that an evolutionarily stable strategy is not necessarily robust against multiple mutations. Precise definition and analysis of “evolutionarily stable strategy against multiple mutations” are not available in the...</citationref>

It is widely recognized that the shape of networks influences both individual and aggregate behavior. This raises the question which types of networks are likely to arise. In this paper we investigate a model of network formation, where players are divided into groups and the costs of a link...