Solving Large Sequential Games with the Excessive Gap Technique

10/07/2018
by   Christian Kroer, et al.
0

There has been tremendous recent progress on equilibrium-finding algorithms for zero-sum imperfect-information extensive-form games, but there has been a puzzling gap between theory and practice. First-order methods have significantly better theoretical convergence rates than any counterfactual-regret minimization (CFR) variant. Despite this, CFR variants have been favored in practice. Experiments with first-order methods have only been conducted on small- and medium-sized games because those methods are complicated to implement in this setting, and because CFR variants have been enhanced extensively for over a decade they perform well in practice. In this paper we show that a particular first-order method, a state-of-the-art variant of the excessive gap technique---instantiated with the dilated entropy distance function---can efficiently solve large real-world problems competitively with CFR and its variants. We show this on large endgames encountered by the Libratus poker AI, which recently beat top human poker specialist professionals at no-limit Texas hold'em. We show experimental results on our variant of the excessive gap technique as well as a prior version. We introduce a numerically friendly implementation of the smoothed best response computation associated with first-order methods for extensive-form game solving. We present, to our knowledge, the first GPU implementation of a first-order method for extensive-form games. We present comparisons of several excessive gap technique and CFR variants.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
02/16/2017

Theoretical and Practical Advances on Smoothing for Extensive-Form Games

Sparse iterative methods, in particular first-order methods, are known t...
research
06/27/2021

Last-iterate Convergence in Extensive-Form Games

Regret-based algorithms are highly efficient at finding approximate Nash...
research
06/05/2020

Sparsified Linear Programming for Zero-Sum Equilibrium Finding

Computational equilibrium finding in large zero-sum extensive-form imper...
research
12/07/2021

Fast Payoff Matrix Sparsification Techniques for Structured Extensive-Form Games

The practical scalability of many optimization algorithms for large exte...
research
03/20/2023

Convergence analysis and acceleration of the smoothing methods for solving extensive-form games

The extensive-form game has been studied considerably in recent years. I...
research
12/20/2021

Fast Algorithms for Poker Require Modelling it as a Sequential Bayesian Game

Many recent results in imperfect information games were only formulated ...
research
06/10/2021

Subgame solving without common knowledge

In imperfect-information games, subgame solving is significantly more ch...

Please sign up or login with your details

Forgot password? Click here to reset