The challenge of poker

By Darse Billings, Aaron M. Davidson, Jonathan Schaeffer, Duane Szafron. 2002

333 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Clinical Psychology, Economics and Econometrics

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Clinical Psychology

In Economics and Econometrics

Citations in the corpus

The State of Solving Large Incomplete-Information Games, and Application to Poker (2010, background): “Poker has emerged as a standard benchmark in this space (Shi and Littman 2002; Billings et al. 2002) for a number of reasons, because (1) it exhibits the richness of reasoning about a probabilistic future, how to interpret others’ actions as signals, and information hiding through careful action…”
Smoothing Techniques for Computing Nash Equilibria of Sequential Games (2010, background): “For these reasons, and others, poker has been identiﬁed as an important challenge problem for the ﬁeld of artiﬁcial intelligence (Billings et al. [1]).”
Computer poker: A review (2011, background): “This type of game tree search works well for games of perfect information, but fails for games involving imperfect information as the missing information ensures that the exact state of the game cannot be known.”
Gradient-Based Algorithms for Finding Nash Equilibria in Extensive Form Games (2007, background): “Table 1 provides the sizes of the four test instances; each models some variant of poker, an important challenge problem in AI [22].”
Approximating game-theoretic optimal strategies for full-scale poker (2003, methodology): “A superior practical method would be to project the set of all hands onto a two-dimensional space consisting of (roll-out) hand strength and hand potential (similar to the hand assessment used in Poki, [Billings et al, 2002]).”
Bandit Based Monte-Carlo Planning (2006, neutral): “Over the years, Monte-Carlo simulation based search algorithms have been used successfully in many non-deterministic and imperfect information games, including backgammon [13], poker [4] and Scrabble [11].”
Monte-Carlo Tree Search: A New Framework for Game AI (2008, methodology): “They have already been applied successfully to many games, including POKER (Billings et al. 2002) and SCRABBLE (Sheppard 2002).”
Solving Heads-Up Limit Texas Hold'em (2015, methodology): “Full-scale poker has been a challenge problem for artificial intelligence, operations research, and psychology, with work going back more than 40 years [Billings et al., 2002].”
Multi-Agent Reinforcement Learning: A Selective Overview of Theories and Algorithms (2019, background): “There has been quest for developing superhuman computer poker programs for over two decades (Billings et al., 2002; Rubin and Watson, 2011).”
Smooth UCT Search in Computer Poker (2015, background): “Recently Bowling et al. [2015] solved two-player LHE after more than 10 years of effort since it had been identified as a fruitful and challenging research topic [Billings et al., 2002].”
Bayes' Bluff: Opponent Modelling in Poker (2005, background): “Existing approaches to opponent modelling have employed a variety of approaches including reinforcement learning [4], neural networks [2], and frequentist statistics [3].”