We develop a model of learning that extends the classic models of reinforcement learning to a continuous … strategies, and allows agents to learn over these sets which speeds up the learning process. We provide an application of our …

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 …

suggests a trade-off of using coarser versus finer representations of the strategy set when it comes to learning. …

suggests a trade-off of using coarser versus finer representations of the strategy set when it comes to learning. …

In standard models of rational learning from experience, prior uncertainties and disagreements recede smoothly as …, uncertainties will surge and core disagreements widen. In general, rational learning tends to bifurcate into calm and turbulent …

externalities for each other. When informational externalities are positive, the agents’ learning processes are mutually … takes a more extreme action, generating a positive feedback loop. The opposite pattern, mutually-limiting learning, arises …