We analyze boundedly rational learning in social networks within binary action environments. We establish how learning … induces learning (i.e., convergence to the optimal action for every agent in every connected network) only in highly … asymmetric environments. In all other environments learning fails in networks with a diameter larger than four. Finally, we …

A learning rule is uncoupled if a player does not condition his strategy on the opponent's payoffs. It is radically …, radically uncoupled learning rules whose period-by-period behavior comes arbitrarily close to Nash equilibrium behavior in any …

While payoff-based learning models are almost exclusively devised for finite action games, where players can test every … action, it is harder to design such learning processes for continuous games. We construct a stochastic learning rule …

We establish convergence of beliefs and actions in a class of one-dimensional learning settings in which the agent …. Applications of our framework include learning by a person who has an incorrect model of a technology she uses or is overconfident … about herself, learning by a representative agent who may misunderstand macroeconomic outcomes, as well as learning by a …

We study perfect Bayesian equilibria of a sequential social learning model in which agents in a network learn about an … neighbors are mutually independent. We introduce a new metric of information diffusion in social learning, which is weaker than …

taking an (irreversible) action. We define \textit{asymptotic learning} as the fraction of agents taking the correct action … converging to one as a society grows large. Under truthful communication, we show that asymptotic learning occurs if (and under … ``information hubs'', which receive and distribute a large amount of information. Asymptotic learning therefore requires information …