No-Regret Learning in Bayesian Games
Abstract
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.
Keywords
Cite
@article{arxiv.1507.00418,
title = {No-Regret Learning in Bayesian Games},
author = {Jason Hartline and Vasilis Syrgkanis and Eva Tardos},
journal= {arXiv preprint arXiv:1507.00418},
year = {2015}
}