Solving Large Imperfect Information Games Using CFR+

Abstract

Counterfactual Regret Minimization and variants (e.g. Public Chance Sampling CFR and Pure CFR) have been known as the best approaches for creating approximate Nash equilibrium solutions for imperfect information games such as poker. This paper introduces CFR${}^{+}$, a new algorithm that typically outperforms the previously known algorithms by an order of magnitude or more in terms of computation time while also potentially requiring less memory.

Cited by in corpus (14)

• Single Deep Counterfactual Regret Minimization
• Algorithms in Multi-Agent Systems: A Holistic Perspective from Reinforcement Learning and Game Theory
• DREAM: Deep Regret minimization with Advantage baselines and Model-free learning
• Unlocking the Potential of Deep Counterfactual Value Networks
• Efficient Deviation Types and Learning for Hindsight Rationality in Extensive-Form Games
• Model-free Neural Counterfactual Regret Minimization with Bootstrap Learning
• Neural Fictitious Self-Play on ELF Mini-RTS
• Last-iterate Convergence in Extensive-Form Games
• Sparsified Linear Programming for Zero-Sum Equilibrium Finding
• Model-Free Learning for Two-Player Zero-Sum Partially Observable Markov Games with Perfect Recall
• Search in Imperfect Information Games
• Optimistic and Adaptive Lagrangian Hedging
• Improving Fictitious Play Reinforcement Learning with Expanding Models
• A simple and numerically stable primal-dual algorithm for computing Nash-equilibria in sequential games with incomplete information