• Corpus ID: 195345728

Most Important Fundamental Rule of Poker Strategy

@inproceedings{Ganzfried2020MostIF,
  title={Most Important Fundamental Rule of Poker Strategy},
  author={Sam Ganzfried and Max Chiswick},
  booktitle={FLAIRS Conference},
  year={2020}
}
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… 

Figures and Tables from this paper

World-class interpretable poker

TLDR
This paper proposes a novel, compact, and easy-to-understand game-state feature representation for Heads-up No-limit (HUNL) Poker, and makes use of globally optimal decision trees, paired with a counterfactual regret minimization (CFR) self-play algorithm, to train the resulting poker bot which produces an entirely interpretable agent.

Human strategic decision making in parametrized games

TLDR
This work presents a new framework that enables human decision makers to make fast decisions without the aid of real-time solvers and demonstrates applicability to a variety of situations including settings with multiple players and imperfect information.

References

SHOWING 1-10 OF 18 REFERENCES

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.

Playing games for security: an efficient exact algorithm for solving Bayesian Stackelberg games

TLDR
This paper considers Bayesian Stackelberg games, in which the leader is uncertain about the types of adversary it may face, and presents an efficient exact algorithm for finding the optimal strategy for the leader to commit to in these games.

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.

Endgame Solving in Large Imperfect-Information Games

TLDR
Theoretically, it is shown that endgame solving can produce highly exploitable strategies in some games; however, it can guarantee a low exploitability in certain games where the opponent is given sufficient exploitative power within the endgame.

Solving Imperfect Information Games Using Decomposition

TLDR
This work presents the first technique for decomposing an imperfect information game into subgames that can be solved independently, while retaining optimality guarantees on the full-game solution, and presents an algorithm for subgame solving which guarantees performance in the whole game, in contrast to existing methods which may have unbounded error.

Refining Subgames in Large Imperfect Information Games

TLDR
This work introduces the notion of subgame margin, a simple value with appealing properties that is guaranteed to find the optimal solution in subgame refinements resulting in large positive margins.

Safe and Nested Subgame Solving for Imperfect-Information Games

TLDR
This work introduces subgame-solving techniques that outperform prior methods both in theory and practice and shows that subgame solving can be repeated as the game progresses down the game tree, leading to far lower exploitability.

DeepStack: Expert-level artificial intelligence in heads-up no-limit poker

TLDR
DeepStack is introduced, an algorithm for imperfect-information settings that combines recursive reasoning to handle information asymmetry, decomposition to focus computation on the relevant decision, and a form of intuition that is automatically learned from self-play using deep learning.

Computing equilibria by incorporating qualitative models?

TLDR
The main algorithm exploits some qualitative model of equilibrium structure as an additional input to find an equilibrium in continuous games and develops the first mixed-integer programming formulations for computing an epsilon-equilibrium in general multiplayer normal and extensive-form games.