DecisionHoldem: Safe Depth-Limited Solving With Diverse Opponents for Imperfect-Information Games
Qibin Zhou, Dongdong Bai, Junge Zhang, Fuqing Duan, Kaiqi Huang
TL;DR
The paper tackles robust decision-making in imperfect-information games, focusing on heads-up no-limit Texas hold'em. It presents DecisionHoldem, which combines a blueprint CFR-based strategy with safe depth-limited subgame solving that accounts for diverse opponent ranges to limit exploitability. The method achieves strong performance, defeating public high-level AIs Slumbot and OpenStack, and the authors release code and tooling to support future research. This open-source contribution lowers barriers to advancing AI in imperfect-information games and provides a practical framework for safe, real-time decision refinement.
Abstract
An imperfect-information game is a type of game with asymmetric information. It is more common in life than perfect-information game. Artificial intelligence (AI) in imperfect-information games, such like poker, has made considerable progress and success in recent years. The great success of superhuman poker AI, such as Libratus and Deepstack, attracts researchers to pay attention to poker research. However, the lack of open-source code limits the development of Texas hold'em AI to some extent. This article introduces DecisionHoldem, a high-level AI for heads-up no-limit Texas hold'em with safe depth-limited subgame solving by considering possible ranges of opponent's private hands to reduce the exploitability of the strategy. Experimental results show that DecisionHoldem defeats the strongest openly available agent in heads-up no-limit Texas hold'em poker, namely Slumbot, and a high-level reproduction of Deepstack, viz, Openstack, by more than 730 mbb/h (one-thousandth big blind per round) and 700 mbb/h. Moreover, we release the source codes and tools of DecisionHoldem to promote AI development in imperfect-information games.