Smoothing Method for Approximate Extensive-Form Perfect Equilibrium

TL;DR

This paper introduces a novel smoothing method to compute approximate extensive-form perfect equilibria, improving strategy quality at low-probability information sets while maintaining fast convergence in large-scale imperfect-information games.

Contribution

It extends first-order methods to equilibrium refinements by developing a smoothing approach for behavioral perturbations in extensive-form games.

Findings

Enhanced strategies at low-probability information sets.

Retains convergence rate of fast algorithms for Nash equilibrium.

Applicable to large-scale imperfect-information games.

Abstract

Nash equilibrium is a popular solution concept for solving imperfect-information games in practice. However, it has a major drawback: it does not preclude suboptimal play in branches of the game tree that are not reached in equilibrium. Equilibrium refinements can mend this issue, but have experienced little practical adoption. This is largely due to a lack of scalable algorithms. Sparse iterative methods, in particular first-order methods, are known to be among the most effective algorithms for computing Nash equilibria in large-scale two-player zero-sum extensive-form games. In this paper, we provide, to our knowledge, the first extension of these methods to equilibrium refinements. We develop a smoothing approach for behavioral perturbations of the convex polytope that encompasses the strategy spaces of players in an extensive-form game. This enables one to compute an approximate variant of extensive-form perfect equilibria. Experiments show that our smoothing approach leads to solutions with dramatically stronger strategies at information sets that are reached with low probability in approximate Nash equilibria, while retaining the overall convergence rate associated with fast algorithms for Nash equilibrium. This has benefits both in approximate equilibrium finding (such approximation is necessary in practice in large games) where some probabilities are low while possibly heading toward zero in the limit, and exact equilibrium computation where the low probabilities are actually zero.