Learning and selfconfirming equilibria in network games

Consider a set of agents who play a network game repeatedly. Agents may not know the network. They may even be unaware that they are interacting with other agents in a network. Possibly, they just understand that their optimal action depends on an unknown state that is, actually, an aggregate of the actions of their neighbors. In each period, every agent chooses an action that maximizes her instantaneous subjective expected payoff and then updates her beliefs according to what she observes. In particular, we assume that each agent only observes her realized payoff. A steady state of the resulting dynamic is a selfconfirming equilibrium given the assumed feedback. We identify conditions on the network externalities, agents' beliefs, and learning dynamics that make agents more or less active (or even inactive) in steady state compared to Nash equilibrium.