English

Revisiting CFR+ and Alternating Updates

Computer Science and Game Theory 2019-02-21 v2
Authors: Neil Burch , Matej Moravcik , Martin Schmid
View on arXiv ↗ PDF ↗

Abstract

The CFR+ algorithm for solving imperfect information games is a variant of the popular CFR algorithm, with faster empirical performance on a range of problems. It was introduced with a theoretical upper bound on solution error, but subsequent work showed an error in one step of the proof. We provide updated proofs to recover the original bound.

Keywords

counterfactual regret minimization game theory

Cite

@article{arxiv.1810.11542,
  title  = {Revisiting CFR+ and Alternating Updates},
  author = {Neil Burch and Matej Moravcik and Martin Schmid},
  journal= {arXiv preprint arXiv:1810.11542},
  year   = {2019}
}

Comments

15 pages, 0 figures. Published in JAIR, Feb. 2019

Related papers

View all related →
Computer Science and Game Theory · Computer Science
Solving Large Imperfect Information Games Using CFR+
Oskari Tammelin
2014-07-21
Computer Science and Game Theory · Computer Science
Solving Imperfect-Information Games via Discounted Regret Minimization
Noam Brown, Tuomas Sandholm
2019-02-22
Machine Learning · Computer Science
Deep (Predictive) Discounted Counterfactual Regret Minimization
Hang Xu, Kai Li, Haobo Fu, Qiang Fu +2
2025-11-12
Machine Learning · Computer Science
Lazy-CFR: fast and near optimal regret minimization for extensive games with imperfect information
Yichi Zhou, Tongzheng Ren, Jialian Li, Dong Yan +1
2018-12-27
Artificial Intelligence · Computer Science
CFR-MIX: Solving Imperfect Information Extensive-Form Games with Combinatorial Action Space
Shuxin Li, Youzhi Zhang, Xinrun Wang, Wanqi Xue +1
2021-05-19
Machine Learning · Computer Science
Bounds for Approximate Regret-Matching Algorithms
Ryan D'Orazio, Dustin Morrill, James R. Wright
2019-12-02
Computer Science and Game Theory · Computer Science
Sync Pure Counterfactual Regret Minimization in Incomplete Information Extensive Form Games
Qi Ju
2023-11-14
Artificial Intelligence · Computer Science
Deep Counterfactual Regret Minimization
Noam Brown, Adam Lerer, Sam Gross, Tuomas Sandholm
2019-05-23
Computer Science and Game Theory · Computer Science
Solving imperfect-information games via exponential counterfactual regret minimization
Huale Li, Xuan Wang, Shuhan Qi, Jiajia Zhang +3
2020-12-07
Machine Learning · Computer Science
Faster Game Solving via Asymmetry of Step Sizes
Linjian Meng, Tianpei Yang, Youzhi Zhang, Zhenxing Ge +1
2025-11-14
Computer Science and Game Theory · Computer Science
Solving Imperfect Information Games Using Decomposition
Neil Burch, Michael Johanson, Michael Bowling
2014-04-22
Machine Learning · Computer Science
RLCFR: Minimize Counterfactual Regret by Deep Reinforcement Learning
Huale Li, Xuan Wang, Fengwei Jia, Yifan Li +3
2020-09-15
Artificial Intelligence · Computer Science
Accelerating Nash Equilibrium Convergence in Monte Carlo Settings Through Counterfactual Value Based Fictitious Play
Ju Qi, Falin Hei, Ting Feng, Dengbing Yi +2
2024-10-29
Computer Science and Game Theory · Computer Science
Combining Counterfactual Regret Minimization with Information Gain to Solve Extensive Games with Unknown Environments
Chen Qiu, Xuan Wang, Tianzi Ma, Yaojun Wen +1
2024-10-30
Computer Science and Game Theory · Computer Science
No-Regret Learning in Extensive-Form Games with Imperfect Recall
Marc Lanctot, Richard Gibson, Neil Burch, Martin Zinkevich +1
2012-05-04
Computer Science and Game Theory · Computer Science
Solving Large Sequential Games with the Excessive Gap Technique
Christian Kroer, Gabriele Farina, Tuomas Sandholm
2018-10-09
Computer Science and Game Theory · Computer Science
Monte Carlo Continual Resolving for Online Strategy Computation in Imperfect Information Games
Michal Sustr, Vojtech Kovarik, Viliam Lisy
2019-03-11
Computer Science and Game Theory · Computer Science
Single Deep Counterfactual Regret Minimization
Eric Steinberger
2019-10-07
Machine Learning · Computer Science
Reevaluating Policy Gradient Methods for Imperfect-Information Games
Max Rudolph, Nathan Lichtle, Sobhan Mohammadpour, Alexandre Bayen +5
2026-05-28
Machine Learning · Computer Science
Minimizing Weighted Counterfactual Regret with Optimistic Online Mirror Descent
Hang Xu, Kai Li, Bingyun Liu, Haobo Fu +3
2024-05-15
Computer Science and Game Theory · Computer Science
Efficient Last-iterate Convergence Algorithms in Solving Games
Linjian Meng, Youzhi Zhang, Zhenxing Ge, Shangdong Yang +5
2025-03-19
Artificial Intelligence · Computer Science
Parallelizing Counterfactual Regret Minimization
Juho Kim, Tuomas Sandholm
2026-05-15
Machine Learning · Computer Science
Hierarchical Deep Counterfactual Regret Minimization
Jiayu Chen, Zhekai Wang, Vaneet Aggarwal
2025-11-12
Computer Science and Game Theory · Computer Science
Sparsified Linear Programming for Zero-Sum Equilibrium Finding
Brian Hu Zhang, Tuomas Sandholm
2020-07-01
Artificial Intelligence · Computer Science
Double Neural Counterfactual Regret Minimization
Hui Li, Kailiang Hu, Zhibang Ge, Tao Jiang +2
2018-12-31
R2 v1 2026-06-23T04:54:15.098Z