James Meade Professor of Economics
Conventional game theory assumes that players are highly rational and that the structure of the game is common knowledge, but unfortunately these conditions are seldom met in practice. We show that there exist simple reinforcement learning rules that allow agents to converge to equilibrium behavior with no information about the structure of the game or even what the other players are doing. This approach can be applied to the design of large systems of interacting agents without relying on a central controller or market clearing mechanism to implement an equilibrium.
Peyton Young is an American game theorist known for his contributions to evolutionary game theory and its application to the study of institutional and technological change, as well as the theory of learning in games. He received his PhD in Mathematics at the University of Michigan in 1970, where he graduated with the Sumner B. Myers thesis prize for his work in combinatorial mathematics. He was Professor of Economics and Public Policy in the School of Public Affairs at the University of Maryland, College Park from 1992 to 1994. Young was Scott & Barbara Black Professor of Economics at the Johns Hopkins University from 1994, until moving to Oxford as James Meade Professor of Economics in 2007. He is a Professorial Fellow at Nuffield College and Research Professor at Johns Hopkins University. He was named a Fellow of the Econometric Society in 1995 and a Fellow of the British Academy in 2007. Peyton Young is also a Senior Fellow for the Center on Social and Economic Dynamics at the Brookings Institution and an external faculty member at the Santa Fe Institute. He served as president of the Game Theory Society from 2006-08. He has published widely on learning in games, the evolution of social norms and institutions, cooperative game theory, bargaining and negotiation, taxation and cost allocation, political representation, voting procedures, and distributive justice.
Loading more stuff…
Hmm…it looks like things are taking a while to load. Try again?