Learning in Repeated Interactions on Networks

TL;DR

This paper analyzes how rational agents learn over time in social networks, showing that the speed of learning is universally bounded regardless of network structure or agent patience.

Contribution

It establishes a universal upper bound on the speed of learning in equilibrium for agents on any network, based solely on private signal distribution.

Findings

Learning speed is bounded by a constant independent of network size and shape.

Equilibrium actions depend on higher order beliefs, complicating analysis.

The bound applies universally across different network configurations.

Abstract

We study how long-lived, rational agents learn in a social network. In every period, after observing the past actions of his neighbors, each agent receives a private signal, and chooses an action whose payoff depends only on the state. Since equilibrium actions depend on higher order beliefs, it is difficult to characterize behavior. Nevertheless, we show that regardless of the size and shape of the network, the utility function, and the patience of the agents, the speed of learning in any equilibrium is bounded from above by a constant that only depends on the private signal distribution.