We introduce a class of reinforcement models where, at each time step t, one ¿rst chooses a random subset A_t of colours (independent of the past) from n colours of balls, and then chooses a colour i from this subset with probability proportional to the number of balls of colour i in the urn raised to the power a > 1. We consider stability of equilibria for such models and establish the existence of phase transitions in a number of examples, including when the colours are the edges of a graph, a context which is a toy model for the formation and reinforcement of neural connections.
Keywords: reinforcement model, Pólya urn, stochastic approximation algorithm, stable equilibria
|Place of Publication||Eindhoven|
|Number of pages||32|
|Publication status||Published - 2014|