Learning in networked systems

The setup of learning in networked systems is a collection of decision making components with local information and limited communication interacting to balance a collective objective with local incentives. This talk presents a tutorial overview of learning in such settings from a game theoretic perspective. While game theory is well known for its traditional role as a modeling framework in social sciences, it is seeing growing interest as a design approach for distributed architecture control. In game theoretic learning, the focus shifts away from equilibrium solution concepts and towards the dynamics of how decision makers reach equilibrium. This talk presents a sampling of results in game theoretic learning from its origins as a “descriptive” model for social systems to its “prescriptive” role as an approach to designing networked control. The talk presents also presents various examples from distributed coordination.