Deep Counterfactual Regret Minimization
Noam Brown, Adam Lerer, Sam Gross, Tuomas Sandholm
Abstract
Counterfactual Regret Minimization (CFR) is the leading algorithm for solving large imperfect-information games. It converges to an equilibrium by iteratively traversing the game tree. In order to deal with extremely large games, abstraction is typically applied before running CFR. The abstracted game is solved with tabular CFR, and its solution is mapped back to the full game. This process can be problematic because aspects of abstraction are often manual and domain specific, abstraction algorithms may miss important strategic nuances of the game, and there is a chicken-and-egg problem because determining a good abstraction requires knowledge of the equilibrium of the game. This paper introduces
BibTeX
@InProceedings{pmlr-v97-brown19b,
title = {Deep Counterfactual Regret Minimization},
author = {Brown, Noam and Lerer, Adam and Gross, Sam and Sandholm, Tuomas},
booktitle = {Proceedings of the 36th International Conference on Machine Learning},
pages = {793--802},
year = {2019},
editor = {Chaudhuri, Kamalika and Salakhutdinov, Ruslan},
volume = {97},
series = {Proceedings of Machine Learning Research},
month = {09--15 Jun},
publisher = {PMLR},
pdf = {http://proceedings.mlr.press/v97/brown19b/brown19b.pdf},
url = {https://proceedings.mlr.press/v97/brown19b.html},
abstract = {Counterfactual Regret Minimization (CFR) is the leading algorithm for solving large imperfect-information games. It converges to an equilibrium by iteratively traversing the game tree. In order to deal with extremely large games, abstraction is typically applied before running CFR. The abstracted game is solved with tabular CFR, and its solution is mapped back to the full game. This process can be problematic because aspects of abstraction are often manual and domain specific, abstraction algorithms may miss important strategic nuances of the game, and there is a chicken-and-egg problem because determining a good abstraction requires knowledge of the equilibrium of the game. This paper introduces