No-Regret Learning in Bayesian Games

نویسندگان

  • Jason D. Hartline
  • Vasilis Syrgkanis
  • Éva Tardos
چکیده

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.

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

No-Regret Learning in Repeated 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 dir...

متن کامل

Pre-Bayesian Games

Work on modelling uncertainty in game theory and economics almost always uses Bayesian assumptions. On the other hand, work in computer science frequently uses non-Bayesian assumptions and appeal to forms of worst case analysis. In this talk we deal with Pre-Bayesian games, games with incomplete information but with no probabilistic assumptions about the environment. We first discuss safety-lev...

متن کامل

Limits and Limitations of No-Regret Learning in Games

We study the limit behavior and performance of no-regret dynamics in general game theoretic settings. We design protocols that achieve both good regret and equilibration guarantees in general games. In terms of arbitrary no-regret dynamics we establish a strong equivalence between them and coarse correlated equilibria. We examine structured game settings where stronger properties can be establi...

متن کامل

On No-Regret Learning, Fictitious Play, and Nash Equilibrium

This paper addresses the question what is the outcome of multi-agent learning via no-regret algorithms in repeated games? Speci cally, can the outcome of no-regret learning be characterized by traditional game-theoretic solution concepts, such as Nash equilibrium? The conclusion of this study is that no-regret learning is reminiscent of ctitious play: play converges to Nash equilibrium in domin...

متن کامل

No-regret Learning in Games

The study of learning dynamics in strategic environments has a long history in economic theory. Many different classes of learning algorithms have been considered in the literature and some have been shown to converge to equilibrium under certain conditions. In this note, I focus on a particular class of learning processes, called no-regret learning. While the no-regret framework was originally...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 2015