Approximating game-theoretic optimal strategies for full-scale poker

By Darse Billings, Neil Burch, Aaron M. Davidson, Robert Craig Holte, Jonathan Schaeffer, Terence Schauenberg, Duane Szafron. 2003

285 citations recorded by the source corpus.

How researchers see this paper

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

Citations in the corpus

Computing Equilibria in Multiplayer Stochastic Games of Imperfect Information (2009, background): “There has been much interest recently in devising strong game-theoretic strategies for a single hand of two-player limit Texas hold’em (e.g., [1, 6, 15]).”
Computer poker: A review (2011, methodology): “As such [9] were forced to combine separate preflop and postflop models to approximate an equilibrium strategy.”
Optimal Unbiased Estimators for Evaluating Agent Performance (2006, methodology): “The first experiment was a self-play match with an experimental version of the advanced pseudo-optimal player (Billings et al. 2003).”
Bayes' Bluff: Opponent Modelling in Poker (2005, methodology): “It has on the order of 10 18 states [1], which makes even straight-forward calculations, such as best response, non-trivial.”
Tractable Objectives for Robust Policy Optimization (2012, background): “Abstraction has proven useful for finding good policies in other large extensive-form-games [2, 18], and so will likely prove effective here.”
A Practical Use of Imperfect Recall (2009, methodology): “In order to make use of game theoretic approaches for computing strategies in these games, we must make use of abstraction techniques (Billings et al. 2003; Gilpin and Sandholm 2007).”
Rethinking Formal Models of Partially Observable Multiagent Decision Making (2019, background): “The idea of decomposing EFGs into subgames dates at least to [2].”
Gradient-Based Algorithms for Finding Nash Equilibria in Extensive Form Games (2007, background): “A recent and fruitful approach to finding strategies for sequential games is to employ lossy abstractions [7,8,6,9,10] to approximate the Nash equilibrium.”
Abstraction pathologies in extensive games (2009, methodology): “The standard approach to this problem is to use abstraction [1].”
Regret Minimization in Games with Incomplete Information (2007, methodology): “Abstraction, both hand-chosen [2] and automated [3], is commonly employed to reduce the game from 10(18) to a tractable number of game states (e.”
Endgame Solving in Large Imperfect-Information Games (2015, methodology): “approximate equilibrium in the abstract game using one of the algorithms described above [2, 7].”
Smoothing Techniques for Computing Nash Equilibria of Sequential Games (2010, background): “[2]; Gilpin and Sandholm [4, 5]; Shi and Littman [20]).”
Time and Space: Why Imperfect Information Games are Hard (2018, methodology): “Abstraction has been popular in game-theoretic poker research, and one method of generating abstract poker games has involved grouping information sets together into a collection called a bin or a bucket [79, 4, 32].”
The State of Solving Large Incomplete-Information Games, and Application to Poker (2010, methodology): “The first approach was to assume rollout of the cards in the later phase(s), that is, no betting and no folding (Billings et al. 2003).”
Hierarchical Abstraction, Distributed Equilibrium Computation, and Post-Processing, with Application to a Champion No-Limit Texas Hold'em Agent (2015, methodology): “Initially abstractions were created manually [24, 2], while nowadays they are created by algorithms [8, 9, 10, 26, 18, 5].”