Superhuman AI for multiplayer poker | ScienceAAASSearchScienceMenu

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.

38 mentions: @WilliamAEden@dylanwiliam@jaguring1@pacocat@page_eco@mcbill@Taghkanic@spsmith1
Date: 2019/07/12 09:47

Referring Tweets

@jaguring1 複数のプレイヤーがいるゲームで、かつ、不完全情報ゲームにおいて、超人レベル。AIの名前は「Pluribus」。複数のプレイヤーが参加するゲームでは強い理論的保証が不足してるけど、超人的な戦略を生成できる、みたいな話 Superhuman AI for multiplayer poker https://t.co/eh7nTAM0LD
@page_eco Artificial Intelligence now beats top professionals in multiple player poker. ➡️ Able to outsmart humans in bluffing https://t.co/9ALIyCnrWB https://t.co/wkpReEfBVq
@WilliamAEden AI achieves superhuman performance in six-player no-limit Texas hold ‘em poker, the final step in poker dominance. https://t.co/wX0pUXHvb6
@dylanwiliam First chess, then Go, now six-player no-limit Texas hold’em poker: artificial intelligence beats the best players on the planet: https://t.co/HKno80Qh0a
@pacocat 6人ポーカー、こんなに早いと思ってなかったけど気になるので論文読む。MonteCarlo CFRで実用レベルのものが作れるという感じなのかな。 https://t.co/m1gIBljU43 2人対戦のNo-limit Hold'emをLibratusが攻略したときにまとめてた資料はこちら。 https://t.co/dAGi0U8SMs
@Mitchell1969 @JonathanLittle @TheAssassinato Here’s the full abstract on that AI (and is Iikely beating everyone online) https://t.co/QkVidxj72p
@mcbill Big doings in the AI world. AI teaches itself poker strategy and trounced multiple pros simultaneously. Incomplete info and non-zero sum outcomes better replicate real world problems: https://t.co/PzVO3YT6Xz cc @amywebb
@ChuckReynolds Scientists have developed an #AI that can beat the top Texas Hold’em Poker players. That’s interesting due to the inherent complexities in multi-player games like poker. https://t.co/Q9ljJRrxS6
@spsmith1 Superhuman AI for multiplayer poker | Science In this paper we described Pluribus, an AI capable of defeating elite human professionals in six-player no-limit Texas hold’em poker, the most commonly played poker format in the world. https://t.co/N3bwjMyaoU