Superhuman AI for multiplayer poker

AI now masters six-player poker Computer programs have shown superiority over humans in two-player games such as chess, Go, and heads-up, no-limit Texas hold'em poker. However, poker games usually include six players—a much trickier challenge for artificial intelligence than the two-player variant. Brown and Sandholm developed a program, dubbed Pluribus, that learned how to play six-player no-limit Texas hold'em by playing against five copies of itself (see the Perspective by Blair and Saffidine). When pitted against five elite professional poker players, or with five copies of Pluribus playing against one professional, the computer performed significantly better than humans over the course of 10,000 hands of poker. Science, this issue p. 885; see also p. 864 An AI dubbed Pluribus performs significantly better than human professionals in six-player no-limit Texas hold’em poker. In recent years there have been great strides in artificial intelligence (AI), with games often serving as challenge problems, benchmarks, and milestones for progress. Poker has served for decades as such a challenge problem. Past successes in such benchmarks, including poker, have been limited to two-player games. However, poker in particular is traditionally played with more than two players. Multiplayer games present fundamental additional issues beyond those in two-player games, and multiplayer poker is a recognized AI milestone. In this paper we present Pluribus, an AI that we show is stronger than top human professionals in six-player no-limit Texas hold’em poker, the most popular form of poker played by humans.

[1]  J. Neumann Zur Theorie der Gesellschaftsspiele , 1928 .

[2]  Gerald Tesauro,et al.  Temporal difference learning and TD-Gammon , 1995, CACM.

[3]  J. Schaeffer One Jump Ahead , 1997, Springer New York.

[4]  Jonathan Schaeffer,et al.  One jump ahead - challenging human supremacy in checkers , 1997, J. Int. Comput. Games Assoc..

[5]  Eric van Damme,et al.  Non-Cooperative Games , 2000 .

[6]  Jonathan Schaeffer,et al.  The challenge of poker , 2002, Artif. Intell..

[7]  Murray Campbell,et al.  Deep Blue , 2002, Artif. Intell..

[8]  Tuomas Sandholm,et al.  Lossless abstraction of imperfect information games , 2007, JACM.

[9]  Xiaotie Deng,et al.  Settling the complexity of computing two-player Nash equilibria , 2007, JACM.

[10]  Paul W. Goldberg,et al.  The Complexity of Computing a Nash Equilibrium , 2009, SIAM J. Comput..

[11]  Richard G. Gibson Regret Minimization in Games and the Development of Champion Multiplayer Computer Poker-Playing Agents , 2014 .

[12]  Neil Burch,et al.  Heads-up limit hold’em poker is solved , 2015, Science.

[13]  Tuomas Sandholm Solving imperfect-information games , 2015, Science.

[14]  Tuomas Sandholm,et al.  Safe Opponent Exploitation , 2015, ACM Trans. Economics and Comput..

[15]  Erik DeBenedictis Rebooting Computers as Learning Machines , 2016, Computer.

[16]  Demis Hassabis,et al.  Mastering the game of Go with deep neural networks and tree search , 2016, Nature.

[17]  Michael Bradley Johanson Robust Strategies and Counter-Strategies: From Superhuman to Optimal Play , 2016 .

[18]  Steven J. Murdoch,et al.  Insecure by Design: Protocols for Encrypted Phone Calls , 2016, Computer.

[19]  Kevin Waugh,et al.  DeepStack: Expert-Level Artificial Intelligence in No-Limit Poker , 2017, ArXiv.

[20]  Michael H. Bowling,et al.  Heads-up limit hold'em poker is solved , 2017, Commun. ACM.

[21]  Kevin Waugh,et al.  DeepStack: Expert-level artificial intelligence in heads-up no-limit poker , 2017, Science.

[22]  Demis Hassabis,et al.  Mastering the game of Go without human knowledge , 2017, Nature.

[23]  Aviad Rubinstein Inapproximability of Nash Equilibrium , 2018, SIAM J. Comput..

[24]  Noam Brown,et al.  Superhuman AI for heads-up no-limit poker: Libratus beats top professionals , 2018, Science.