DecisionHoldem: Safe Depth-Limited Solving With Diverse Opponents for Imperfect-Information Games
This work addresses the lack of open-source code in Texas hold'em AI development, providing a tool to promote progress in imperfect-information games.
The paper tackles the problem of developing a high-level AI for heads-up no-limit Texas hold'em poker by introducing DecisionHoldem, which uses safe depth-limited subgame solving with opponent hand ranges to reduce exploitability, and it defeats the strongest openly available agents, Slumbot and Openstack, by over 730 mbb/h and 700 mbb/h respectively.
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.