Poster
No-Regret Learning in Bayesian Games
Jason Hartline · Vasilis Syrgkanis · Eva Tardos

Thu Dec 10th 11:00 AM -- 03:00 PM @ 210 C #81 #None
in Poster Session »

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.

Author Information

Jason Hartline (Northwestern University)
Vasilis Syrgkanis (Microsoft Research)
Eva Tardos (Cornell University)

More from the Same Authors