Dynamic social learning under graph constraints

We introduce a model of graph-constrained dynamic choice with reinforcement modeled by positively $\alpha$-homogeneous rewards. We show that its empirical process, which can be written as a stochastic approximation recursion with Markov noise, has the same probability law as a certain vertex reinforced random walk. Thus the limiting differential equation that it tracks coincides with the forward Kolmogorov equation for the latter, which in turn is a scaled version of a special instance of replicator dynamics with potential. We use this equivalence to show that for $\alpha > 0$, the asymptotic outcome concentrates around the optimum in a certain limiting sense when `annealed' by letting $\alpha\uparrow\infty$ slowly.