DeepAI AI Chat
Log In Sign Up

Theoretical and Practical Advances on Smoothing for Extensive-Form Games

02/16/2017
by   Christian Kroer, et al.
Carnegie Mellon University
0

Sparse iterative methods, in particular first-order methods, are known to be among the most effective in solving large-scale two-player zero-sum extensive-form games. The convergence rates of these methods depend heavily on the properties of the distance-generating function that they are based on. We investigate the acceleration of first-order methods for solving extensive-form games through better design of the dilated entropy function---a class of distance-generating functions related to the domains associated with the extensive-form games. By introducing a new weighting scheme for the dilated entropy function, we develop the first distance-generating function for the strategy spaces of sequential games that has no dependence on the branching factor of the player. This result improves the convergence rate of several first-order methods by a factor of Ω(b^dd), where b is the branching factor of the player, and d is the depth of the game tree. Thus far, counterfactual regret minimization methods have been faster in practice, and more popular, than first-order methods despite their theoretically inferior convergence rates. Using our new weighting scheme and practical tuning we show that, for the first time, the excessive gap technique can be made faster than the fastest counterfactual regret minimization algorithm, CFR+, in practice.

READ FULL TEXT

page 1

page 2

page 3

page 4

10/07/2018

Solving Large Sequential Games with the Excessive Gap Technique

There has been tremendous recent progress on equilibrium-finding algorit...
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...
02/19/2020

Stochastic Regret Minimization in Extensive-Form Games

Monte-Carlo counterfactual regret minimization (MCCFR) is the state-of-t...
02/13/2019

Stable-Predictive Optimistic Counterfactual Regret Minimization

The CFR framework has been a powerful tool for solving large-scale exten...
03/05/2023

Uncoupled and Convergent Learning in Two-Player Zero-Sum Markov Games

We revisit the problem of learning in two-player zero-sum Markov games, ...