DeepStack: expert-level artificial intelligence in heads-up no-limit poker. Artificial intelligence has seen several breakthroughs in recent years, with games often serving as milestones. A common feature of these games is that players have perfect information. Poker, the quintessential game of imperfect information, is a long-standing challenge problem in artificial intelligence. We introduce DeepStack, an algorithm for imperfect-information settings. It 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. In a study involving 44,000 hands of poker, DeepStack defeated, with statistical significance, professional poker players in heads-up no-limit Texas hold’em. The approach is theoretically sound and is shown to produce strategies that are more difficult to exploit than prior approaches.

References in zbMATH (referenced in 18 articles )

Showing results 1 to 18 of 18.
Sorted by year (citations)

  1. Fornasier, Massimo; Klock, Timo; Rauchensteiner, Michael: Robust and resource-efficient identification of two hidden layer neural networks (2022)
  2. Janson, N. B.; Kloeden, P. E.: Mathematical consistency and long-term behaviour of a dynamical system with a self-organising vector field (2022)
  3. Kovařík, Vojtěch; Schmid, Martin; Burch, Neil; Bowling, Michael; Lisý, Viliam: Rethinking formal models of partially observable multiagent decision making (2022)
  4. Kroer, Christian; Peysakhovich, Alexander; Sodomka, Eric; Stier-Moses, Nicolas E.: Computing large market equilibria using abstractions (2022)
  5. Caballero, William N.; Lunday, Brian J.; Uber, Richard P.: Identifying behaviorally robust strategies for normal form games under varying forms of uncertainty (2021)
  6. Castiglioni, Matteo; Marchesi, Alberto; Gatti, Nicola: Committing to correlated strategies with multiple leaders (2021)
  7. Chen, Yuqi; Zhang, Xiaoyu; Xie, Yi; Miao, Meixia; Ma, Xu: CECMLP: new cipher-based evaluating collaborative multi-layer perceptron scheme in federated learning (2021)
  8. Bard, Nolan; Foerster, Jakob N.; Chandar, Sarath; Burch, Neil; Lanctot, Marc; Song, H. Francis; Parisotto, Emilio; Dumoulin, Vincent; Moitra, Subhodeep; Hughes, Edward; Dunning, Iain; Mourad, Shibl; Larochelle, Hugo; Bellemare, Marc G.; Bowling, Michael: The Hanabi challenge: a new frontier for AI research (2020)
  9. Čermák, Jiří; Lisý, Viliam; Bošanský, Branislav: Automated construction of bounded-loss imperfect-recall abstractions in extensive-form games (2020)
  10. Kovařík, Vojtěch; Lisý, Viliam: Analysis of Hannan consistent selection for Monte Carlo tree search in simultaneous move games (2020)
  11. Kroer, Christian; Sandholm, Tuomas: Limited lookahead in imperfect-information games (2020)
  12. Kroer, Christian; Waugh, Kevin; Kılınç-Karzan, Fatma; Sandholm, Tuomas: Faster algorithms for extensive-form game solving via improved smoothing functions (2020)
  13. Mazzolini, Andrea; Celani, Antonio: Generosity, selfishness and exploitation as optimal greedy strategies for resource sharing (2020)
  14. Brown, Noam; Sandholm, Tuomas: Superhuman AI for multiplayer poker (2019)
  15. Čermák, Jiří; Bošanský, Branislav; Horák, Karel; Lisý, Viliam; Pěchouček, Michal: Approximating maxmin strategies in imperfect recall games using A-loss recall property (2018)
  16. Ganzfried, Sam; Nowak, Austin; Pinales, Joannier: Successful Nash equilibrium agent for a three-player imperfect-information game (2018)
  17. Ganzfried, Sam; Yusuf, Farzana: Computing human-understandable strategies: deducing fundamental rules of poker strategy (2017)
  18. Moravčík, Matej; Schmid, Martin; Burch, Neil; Lisý, Viliam; Morrill, Dustin; Bard, Nolan; Davis, Trevor; Waugh, Kevin; Johanson, Michael; Bowling, Michael: DeepStack: expert-level artificial intelligence in heads-up no-limit poker (2017)