Superhuman AI for heads-up no-limit poker: Libratus beats top professionals. No-limit Texas hold’em is the most popular form of poker. Despite artificial intelligence (AI) successes in perfect-information games, the private information and massive game tree have made no-limit poker difficult to tackle. We present Libratus, an AI that, in a 120,000-hand competition, defeated four top human specialist professionals in heads-up no-limit Texas hold’em, the leading benchmark and long-standing challenge problem in imperfect-information game solving. Our game-theoretic approach features application-independent techniques: an algorithm for computing a blueprint for the overall strategy, an algorithm that fleshes out the details of the strategy for subgames that are reached during play, and a self-improver algorithm that fixes potential weaknesses that opponents have identified in the blueprint strategy.

References in zbMATH (referenced in 11 articles , 1 standard article )

Showing results 1 to 11 of 11.
Sorted by year (citations)

  1. Kovařík, Vojtěch; Schmid, Martin; Burch, Neil; Bowling, Michael; Lisý, Viliam: Rethinking formal models of partially observable multiagent decision making (2022)
  2. Kroer, Christian; Peysakhovich, Alexander; Sodomka, Eric; Stier-Moses, Nicolas E.: Computing large market equilibria using abstractions (2022)
  3. Castiglioni, Matteo; Marchesi, Alberto; Gatti, Nicola: Committing to correlated strategies with multiple leaders (2021)
  4. Fu, Justin; Tacchetti, Andrea; Perolat, Julien; Bachrach, Yoram: Evaluating strategic structures in multi-agent inverse reinforcement learning (2021)
  5. 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)
  6. Čermák, Jiří; Lisý, Viliam; Bošanský, Branislav: Automated construction of bounded-loss imperfect-recall abstractions in extensive-form games (2020)
  7. Han, The Anh; Pereira, Luis Moniz; Santos, Francisco C.; Lenaerts, Tom: To regulate or not: a social dynamics analysis of an idealised AI race (2020)
  8. Kovařík, Vojtěch; Lisý, Viliam: Analysis of Hannan consistent selection for Monte Carlo tree search in simultaneous move games (2020)
  9. Parras, Juan; Zazo, Santiago: A distributed algorithm to obtain repeated games equilibria with discounting (2020)
  10. Brown, Noam; Sandholm, Tuomas: Superhuman AI for multiplayer poker (2019)
  11. Brown, Noam; Sandholm, Tuomas: Superhuman AI for heads-up no-limit poker: Libratus beats top professionals (2018)