No-Regret Learning in Extensive-Form Games with Imperfect Recall

05/03/2012
by   Marc Lanctot, et al.
0

Counterfactual Regret Minimization (CFR) is an efficient no-regret learning algorithm for decision problems modeled as extensive games. CFR's regret bounds depend on the requirement of perfect recall: players always remember information that was revealed to them and the order in which it was revealed. In games without perfect recall, however, CFR's guarantees do not apply. In this paper, we present the first regret bound for CFR when applied to a general class of games with imperfect recall. In addition, we show that CFR applied to any abstraction belonging to our general class results in a regret bound not just for the abstract game, but for the full game as well. We verify our theory and show how imperfect recall can be used to trade a small increase in regret for a significant reduction in memory in three domains: die-roll poker, phantom tic-tac-toe, and Bluff.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
03/14/2018

Constructing Imperfect Recall Abstractions to Solve Large Extensive-Form Games

Extensive-form games are an important model of finite sequential interac...
research
10/10/2018

Lazy-CFR: a fast regret minimization algorithm for extensive games with imperfect information

In this paper, we focus on solving two-player zero-sum extensive games w...
research
10/07/2019

Combining No-regret and Q-learning

Counterfactual Regret Minimization (CFR) has found success in settings l...
research
02/23/2020

A Bridge between Polynomial Optimization and Games with Imperfect Recall

We provide several positive and negative complexity results for solving ...
research
12/06/2019

Alternative Function Approximation Parameterizations for Solving Games: An Analysis of f-Regression Counterfactual Regret Minimization

Function approximation is a powerful approach for structuring large deci...
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
07/13/2017

Armstrong's Axioms and Navigation Strategies

The paper investigates navigability with imperfect information. It shows...

Please sign up or login with your details

Forgot password? Click here to reset