Reflections on the first man vs. machine no-limit Texas hold 'em competition

@article{Ganzfried2016ReflectionsOT,
  title={Reflections on the first man vs. machine no-limit Texas hold 'em competition},
  author={Sam Ganzfried},
  journal={SIGecom Exch.},
  year={2016},
  volume={14},
  pages={2-15}
}
  • Sam Ganzfried
  • Published 2016
  • Computer Science, Economics, Mathematics
  • SIGecom Exch.
The first ever human vs. computer no-limit Texas hold 'em competition took place from April 24--May 8, 2015 at River's Casino in Pittsburgh, PA. In this article I present my thoughts on the competition design, agent architecture, and lessons learned. 

Figures and Topics from this paper

Computing Human-Understandable Strategies: Deducing Fundamental Rules of Poker Strategy
TLDR
This work creates a large training set of game instances and solutions, by randomly selecting the information probabilities, and presents algorithms that learn from the training instances to perform well in games with unseen distributions. Expand
Learning Human-Understandable Strategies
TLDR
This work studies poker games where private information distributions can be arbitrary, and creates a large training set of game instances and solutions, by randomly selecting the private information probabilities, and presents algorithms that learn from the training instances in order to perform well in games with unseen information distributions. Expand
Computing Human-Understandable Strategies
TLDR
This work creates a large training set of game instances and solutions, by randomly selecting the information probabilities, and presents algorithms that learn from the training instances in order to perform well in games with unseen information distributions. Expand
Eqilibrium Approximation Quality of Current No-Limit Poker Bots
TLDR
This paper presents a simple and computationally inexpensive Local Best Response method for computing an approximate lower bound on the value of the best response strategy, and shows that existing poker-playing programs are remarkably poor Nash equilibrium approximations. Expand
Technical Report Column
TLDR
This work presents a meta-anatomy of noncommutative Valiant’s Classes: Structure and Complete Problems, which aims to clarify the role of Non-Commutative Formulas in the development of scalable scalable systems. Expand

References

SHOWING 1-10 OF 116 REFERENCES
Reflections on the First Man versus Machine No-Limit Texas Hold 'em Competition
TLDR
The first human versus computer no-limit Texas hold ‘em competition took place from April 24–May 8, 2015 at River’s Casino in Pittsburgh, PA and my thoughts on the competition design, agent architecture, and lessons learned are presented. Expand
Heads-up limit hold’em poker is solved
TLDR
It is announced that heads-up limit Texas hold’em is now essentially weakly solved, and this computation formally proves the common wisdom that the dealer in the game holds a substantial advantage. Expand
A heads-up no-limit Texas Hold'em poker player: discretized betting models and automatically generated equilibrium-finding programs
TLDR
Tartanian, a game theory-based player for heads-up no-limit Texas Hold'em poker, is presented and a new technique for automatically generating the source code of an equilibrium-finding algorithm from an XML-based description of a game is developed. Expand
Hierarchical Abstraction, Distributed Equilibrium Computation, and Post-Processing, with Application to a Champion No-Limit Texas Hold'em Agent
TLDR
A distributed version of the most commonly used equilibrium-finding algorithm, counterfactual regret minimization (CFR), is introduced, which enables CFR to scale to dramatically larger abstractions and numbers of cores and a family of post-processing techniques that outperform prior ones are introduced. Expand
A Competitive Texas Hold'em Poker Player via Automated Abstraction and Real-Time Equilibrium Computation
TLDR
It is demonstrated that the game theory-based heads-up Texas Hold'em poker player, GS1, which incorporates very little poker-specific knowledge, is competitive with leading poker-playing programs which incorporate extensive domain knowledge, as well as with advanced human players. Expand
Better automated abstraction techniques for imperfect information games, with application to Texas Hold'em poker
TLDR
Two new approximation methods for computing game-theoretic strategies for sequential games of imperfect information are presented, and each of the two new techniques improves performance dramatically in Texas Hold'em poker. Expand
A Practical Use of Imperfect Recall
TLDR
It is shown that removing this restriction can provide considerable empirical advantages when modeling extremely large extensive games, in particular, it allows granularity of the most relevant observations without requiring decisions to be contingent on all past observations. Expand
Measuring the Size of Large No-Limit Poker Games
TLDR
A simple algorithm for quickly computing the size of two-player no-limit poker games is described, an implementation of this algorithm is provided, and for the first time precise counts of the number of game states, information sets, actions and terminal nodes in the no- limit poker games played in the Annual Computer Poker Competition are presented. Expand
Action Translation in Extensive-Form Games with Large Action Spaces: Axioms, Paradoxes, and the Pseudo-Harmonic Mapping
TLDR
This work presents a new mapping that satisfies certain natural desiderata and has significantly lower exploitability than the prior mappings, and shows that it is possible to improve performance by including suboptimal actions in the authors' abstraction and excluding optimal actions. Expand
Approximating Game-Theoretic Optimal Strategies for Full-scale Poker
TLDR
The computation of the first complete approximations of game-theoretic optimal strategies for full-scale poker is addressed, and linear programming solutions to the abstracted game are used to create substantially improved poker-playing programs. Expand
...
1
2
3
4
5
...