2019/06/08 by Sam Ganzfried, Ganzfried, Sam, Max Chiswick +1 · 2 citations
Computer Science · Economics, Econometrics and Finance · Mathematics · Psychology · #Artificial Intelligence (cs.AI) #Artificial Intelligence in Games #Artificial intelligence #Best response #Computer Science and Game Theory (cs.GT) #Computer science #Decision maker #Economics #FOS: Computer and information sciences #FOS: Economics and business #Fictitious play #Gambling Behavior and Treatments #Game theory #Imperfect #Limit (mathematics) #Machine Learning (cs.LG) #Machine learning #Mathematical economics #Mathematics #Nash equilibrium #Operations research #Perfect information #Repeated game #Simple (philosophy) #Sports Analytics and Performance #Theoretical Economics (econ.TH) #cs.AI #cs.GT #cs.LG #econ.TH
paper · pdf · doi:10.48550/arxiv.1906.09895
published in arXiv (Cornell University) (Cornell University)
openalex publication_date 2019/06/08 · arxiv created 2020/02/21 · arxiv updated 2022/06/28 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/05
Poker is a large complex game of imperfect information, which has been singled out as a major AI challenge problem. Recently there has been a series of breakthroughs culminating in agents that have successfully defeated the strongest human players in two-player no-limit Texas hold 'em. The strongest agents are based on algorithms for approximating Nash equilibrium strategies, which are stored in massive binary files and unintelligible to humans. A recent line of research has explored approaches for extrapolating knowledge from strong game-theoretic strategies that can be understood by humans. This would be useful when humans are the ultimate decision maker and allow humans to make better decisions from massive algorithmically-generated strategies. Using techniques from machine learning we have uncovered a new simple, fundamental rule of poker strategy that leads to a significant improvement in performance over the best prior rule and can also easily be applied by human players.