No-Regret Learning in Bayesian Games

Recent price-of-anarchy analyses of games of complete information suggest that coarse correlated equilibria, which characterize outcomes resulting from no-regret learning dynamics, have near-optimal welfare. This work provides two main technical results that lift this conclusion to games of incomplete information, a.k.a., Bayesian games. First, near-optimal welfare in Bayesian games follows directly from the smoothness-based proof of near-optimal welfare in the same game when the private information is public. Second, no-regret learning dynamics converge to Bayesian coarse correlated equilibrium in these incomplete information games. These results are enabled by interpretation of a Bayesian game as a stochastic game of complete information.

[1]  Christos H. Papadimitriou,et al.  Worst-case equilibria , 1999 .

[2]  D. Bergemann,et al.  Correlated Equilibrium in Games with Incomplete Information , 2011 .

[3]  Allan Borodin,et al.  Price of anarchy for greedy auctions , 2009, SODA '10.

[4]  Tim Roughgarden,et al.  Intrinsic robustness of the price of anarchy , 2009, STOC '09.

[5]  F. Forges,et al.  Five legitimate definitions of correlated equilibrium in games with incomplete information , 1993 .

[6]  Evangelos Markakis,et al.  Inefficiency of Standard Multi-unit Auctions , 2013, ESA.

[7]  Shmuel Zamir,et al.  Asymmetric First-Price Auctions With Uniform Distributions: Analytic Solutions to the General Case , 2007 .

[8]  Christos H. Papadimitriou,et al.  Worst-case Equilibria , 1999, STACS.

[9]  Éva Tardos,et al.  Composable and efficient mechanisms , 2012, STOC '13.

[10]  John N. Tsitsiklis,et al.  Efficiency loss in a network resource allocation game: the case of elastic supply , 2004, IEEE Transactions on Automatic Control.

[11]  Stephen Morris,et al.  Games with Incomplete Information , 2011 .

[12]  Yang Cai,et al.  Simultaneous bayesian auctions and computational complexity , 2014, EC.

[13]  Adrian Vetta,et al.  Nash equilibria in competitive societies, with applications to facility location, traffic routing and auctions , 2002, The 43rd Annual IEEE Symposium on Foundations of Computer Science, 2002. Proceedings..

[14]  Renato Paes Leme,et al.  Bounding the inefficiency of outcomes in generalized second price auctions , 2012, J. Econ. Theory.

[15]  Mohammad Taghi Hajiaghayi,et al.  Regret minimization and the price of total anarchy , 2008, STOC.