Learning in Bayesian Games
Abstract:
Auctions are modeled as Bayesian games with continuous type and action spaces. Determining equilibria in auction games is computationally hard in general and no exact solution theory is known. We introduce an algorithmic framework in which we discretize type and action space and then learn distributional strategies via online optimization algorithms. We show that the equilibrium of the discretized game approximates an equilibrium in the continuous game. In a wide variety of auction games, we provide empirical evidence that the approach approximates the analytical (pure) Bayes-Nash equilibrium closely. In standard models where agents are symmetric, we find equilibrium in seconds. The method allows for interdependent valuations and different types of utility functions and it provides a foundation for broadly applicable equilibrium solvers that can push the boundaries of equilibrium analysis in auction markets and beyond.
About Martin Bichler:
Martin Bichler is heading the Decision Sciences & Systems lab and is a full professor at the Department of Computer Science of the Technical University of Munich (TUM). He is also affiliated with the TUM School of Management. Martin received his MSc degree from the Technical University of Vienna, and his Ph. D. as well as his Habilitation from the Vienna University of Economics and Business. He was a research fellow at UC Berkeley, and a research staff member at the IBM T. J. Watson Research Center, Yorktown Heights, New York. Later, he was a visiting scholar at the University of Cambridge, at HP Labs Palo Alto, at the Department of Economics at Yale University, and at the Department of Economics at Stanford University. In the fall 2023, he was a Research Professor at the Simons Laufer Mathematical Sciences Institute in Berkeley. Martin was a president of the INFORMS Section on Auctions and Market Design, an editor-in-chief of the BISE journal, and a fellow of the Agora Group on Market Design at the University of New South Wales. He is the spokesperson of the DFG-funded research training group AdONE, and serves at the editorial board of several journals such as Management Science, Information Systems Research, and Operations Research.
Language: English
This is a free seminar. Registration is mandatory.