Publication | Closed Access
Superhuman AI for multiplayer poker
577
Citations
18
References
2019
Year
Artificial IntelligenceMultiplayer PokerGame AiReward HackingMechanism DesignEngineeringSuperhuman AiGame TheoryBusinessComputer ScienceIntelligent SystemsRobot LearningComputational Game TheoryGamesOpponent ModellingGeneral Game PlayingGame DesignAi Milestone
Artificial intelligence has advanced through game benchmarks, yet multiplayer poker—especially six‑player no‑limit Texas hold'em—remains an unresolved AI milestone due to its complexity beyond two‑player games. The study introduces Pluribus, an AI designed to outperform top human professionals in six‑player no‑limit Texas hold'em poker. Pluribus achieved performance surpassing top 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.
| Year | Citations | |
|---|---|---|
Page 1
Page 1