Equilibrium Approximation Quality of Current No-Limit Poker Bots

Abstract

Approximating a Nash equilibrium is currently the best performing approach for creating poker-playing programs. While for the simplest variants of the game, it is possible to evaluate the quality of the approximation by computing the value of the best response strategy, this is currently not computationally feasible for larger variants of the game, such as heads-up no-limit Texas hold'em. In this paper, we present a simple and computationally inexpensive Local Best Response method for computing an approximate lower bound on the value of the best response strategy. Using this method, we show that existing poker-playing programs, based on solving abstract games, are remarkably poor Nash equilibrium approximations.

arXiv commentTo appear at AAAI-17 Workshop on Computer Poker and Imperfect Information Games

References in corpus (1)

• AIVAT: A New Variance Reduction Technique for Agent Evaluation in Imperfect Information Games

Cited by in corpus (10)

• DeepStack: Expert-Level Artificial Intelligence in No-Limit Poker
• Learning to Play No-Press Diplomacy with Best Response Policy Iteration
• Single Deep Counterfactual Regret Minimization
• DREAM: Deep Regret minimization with Advantage baselines and Model-free learning
• Unlocking the Potential of Deep Counterfactual Value Networks
• The Advantage Regret-Matching Actor-Critic
• Neural Fictitious Self-Play on ELF Mini-RTS
• Approximate exploitability: Learning a best response in large games
• Search in Imperfect Information Games
• Automated Construction of Bounded-Loss Imperfect-Recall Abstractions in Extensive-Form Games