Hedging in games: Faster convergence of external and swap regrets

06/08/2020
by   Xi Chen, et al.
0

We consider the setting where players run the Hedge algorithm or its optimistic variant <cit.> to play an n-action game repeatedly for T rounds. 1) For two-player games, we show that the regret of optimistic Hedge decays at Õ( 1/T ^5/6 ), improving the previous bound O(1/T^3/4) by <cit.>. 2) In contrast, we show that the convergence rate of vanilla Hedge is no better than Ω̃(1/ √(T)), addressing an open question posted in <cit.>. For general m-player games, we show that the swap regret of each player decays at rate Õ(m^1/2 (n/T)^3/4) when they combine optimistic Hedge with the classical external-to-internal reduction of Blum and Mansour <cit.>. The algorithm can also be modified to achieve the same rate against itself and a rate of Õ(√(n/T)) against adversaries. Via standard connections, our upper bounds also imply faster convergence to coarse correlated equilibria in two-player games and to correlated equilibria in multiplayer games.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
08/16/2021

Near-Optimal No-Regret Learning in General Games

We show that Optimistic Hedge – a common variant of multiplicative-weigh...
research
03/22/2022

Optimistic Mirror Descent Either Converges to Nash or to Strong Coarse Correlated Equilibria in Bimatrix Games

We show that, for any sufficiently small fixed ϵ > 0, when both players ...
research
11/11/2021

Near-Optimal No-Regret Learning for Correlated Equilibria in Multi-Player General-Sum Games

Recently, Daskalakis, Fishelson, and Golowich (DFG) (NeurIPS`21) showed ...
research
02/13/2023

A regularized variance-reduced modified extragradient method for stochastic hierarchical games

The theory of learning in games has so far focused mainly on games with ...
research
10/14/2019

Learning to Correlate in Multi-Player General-Sum Sequential Games

In the context of multi-player, general-sum games, there is an increasin...
research
12/20/2022

Anticipatory Fictitious Play

Fictitious play is an algorithm for computing Nash equilibria of matrix ...
research
05/29/2019

Extra-gradient with player sampling for provable fast convergence in n-player games

Data-driven model training is increasingly relying on finding Nash equil...

Please sign up or login with your details

Forgot password? Click here to reset