Electrical, Computer, & Systems Engineering Seminar: Information and Incentives in Learning and Decision Making on Networks

Networks play a central role in determining the outcomes of a variety of socio-technological and economic interactions. Examples include investing in security, sharing of congestible resources, and learning by teams of agents, in network environments. In this talk, I aim to analyze the role of information and incentives in distributed learning and decision making in such problems. 

I will first discuss the role of information sharing in a multi-agent (reinforcement) learning problem. We study learning and decision making by agents who have heterogeneous information about their unknown, partially observable environment. We identify two benefits of information sharing between such agents: it facilitates coordination among them, and further enhances the learning rate of both better informed and less informed agents. We show however that these benefits will depend on the communication timing, in that delayed information sharing may be preferred in certain scenarios. 

I will then present a framework for characterizing the effects of the network topology on strategic decision making over networks. Specifically, we establish a connection between the equilibrium outcomes of network games with non-linear (resp. linear) best-response functions, and variational inequality (resp. linear complementarity) problems. Through these connections, we outline conditions for existence, uniqueness, and stability of equilibria in these games, extending several existing results in the literature. We further discuss the effects of the network topology on the design of incentive mechanisms in such settings, with applications in improving cybersecurity.