We report the findings of experiments designed to study how people learn in network games. Network games offer new … find that learning depends on network position. Participants in more complex environments (with more network neighbors …) tend to resort to simpler rules compared to those with only one network neighbor. …

networks are either complete or have the stararchitecture. Moreover, the process of network formation has powerful effects on … individualbehavior: if costs of forming links are low then players coordinate on the risk-dominant action,while if costs of forming links …

convergence is 1/T, regardless of the size of the network. In contrast, arbitrary n-person zero-sum games with bilinear payoff … requires a condition on bilateral payoffs or, alternatively, that the network is acyclic. Our results hold also for the …

This paper studies adaptive learning in the class of weighted network games. This class of games includes applications … defense expenditures within allied nations. We show that for every weighted network game, the set of pure Nash equilibria is … show that quite general learning processes converge to a Nash equilibrium of a weighted network game if every player …