Efficient Phi-Regret Minimization in Extensive-Form Games via Online Mirror Descent

TL;DR

This paper introduces a polynomial-time online mirror descent approach for learning equilibria in extensive-form games, achieving optimal regret bounds and connecting game-theoretic algorithms with mirror descent techniques.

Contribution

It establishes a novel equivalence between Phi-Hedge algorithms and online mirror descent for EFGs, enabling efficient equilibrium learning with improved regret guarantees.

Findings

Polynomial-time algorithms for EFCE with optimal regret.

Equivalence between Phi-Hedge and OMD in EFGs.

Achieved matching lower bounds for bandit-feedback regret.

Abstract

A conceptually appealing approach for learning Extensive-Form Games (EFGs) is to convert them to Normal-Form Games (NFGs). This approach enables us to directly translate state-of-the-art techniques and analyses in NFGs to learning EFGs, but typically suffers from computational intractability due to the exponential blow-up of the game size introduced by the conversion. In this paper, we address this problem in natural and important setups for the \emph{$\Phi$-Hedge} algorithm -- A generic algorithm capable of learning a large class of equilibria for NFGs. We show that $\Phi$-Hedge can be directly used to learn Nash Equilibria (zero-sum settings), Normal-Form Coarse Correlated Equilibria (NFCCE), and Extensive-Form Correlated Equilibria (EFCE) in EFGs. We prove that, in those settings, the \emph{$\Phi$-Hedge} algorithms are equivalent to standard Online Mirror Descent (OMD) algorithms for EFGs with suitable dilated regularizers, and run in polynomial time. This new connection further allows us to design and analyze a new class of OMD algorithms based on modifying its log-partition function. In particular, we design an improved algorithm with balancing techniques that achieves a sharp $\widetilde{\mathcal{O}}(\sqrt{XAT})$ EFCE-regret under bandit-feedback in an EFG with $X$ information sets, $A$ actions, and $T$ episodes. To our best knowledge, this is the first such rate and matches the information-theoretic lower bound.