Alert button
Picture for Vasilis Syrgkanis

Vasilis Syrgkanis

Alert button

Fast Convergence of Regularized Learning in Games

Dec 10, 2015
Vasilis Syrgkanis, Alekh Agarwal, Haipeng Luo, Robert E. Schapire

Figure 1 for Fast Convergence of Regularized Learning in Games
Figure 2 for Fast Convergence of Regularized Learning in Games

We show that natural classes of regularized learning algorithms with a form of recency bias achieve faster convergence rates to approximate efficiency and to coarse correlated equilibria in multiplayer normal form games. When each player in a game uses an algorithm from our class, their individual regret decays at $O(T^{-3/4})$, while the sum of utilities converges to an approximate optimum at $O(T^{-1})$--an improvement upon the worst case $O(T^{-1/2})$ rates. We show a black-box reduction for any algorithm in the class to achieve $\tilde{O}(T^{-1/2})$ rates against an adversary, while maintaining the faster rates against algorithms in the class. Our results extend those of [Rakhlin and Shridharan 2013] and [Daskalakis et al. 2014], who only analyzed two-player zero-sum games for specific algorithms.

Viaarxiv icon

No-Regret Learning in Bayesian Games

Nov 19, 2015
Jason Hartline, Vasilis Syrgkanis, Eva Tardos

Figure 1 for 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.

Viaarxiv icon