A Survey on Game Theory Optimal Poker
This is an incremental survey paper that synthesizes existing knowledge on poker AI for researchers and practitioners in the field.
This survey compares Game Theory Optimal (GTO) poker to exploitative poker and discusses abstraction techniques, betting models, and strategies used by successful poker bots like Tartanian and Pluribus, while exploring challenges in multi-player games and the role of machine learning in strategy development.
Poker is in the family of imperfect information games unlike other games such as chess, connect four, etc which are perfect information game instead. While many perfect information games have been solved, no non-trivial imperfect information game has been solved to date. This makes poker a great test bed for Artificial Intelligence research. In this paper we firstly compare Game theory optimal poker to Exploitative poker. Secondly, we discuss the intricacies of abstraction techniques, betting models, and specific strategies employed by successful poker bots like Tartanian[1] and Pluribus[6]. Thirdly, we also explore 2-player vs multi-player games and the limitations that come when playing with more players. Finally, this paper discusses the role of machine learning and theoretical approaches in developing winning strategies and suggests future directions for this rapidly evolving field.