DeepStack: Expert-level artificial intelligence in heads-up no-limit poker

Result code in IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F17%3A10366955" target="_blank" >RIV/00216208:11320/17:10366955 - isvavai.cz</a>

Alternative codes found

RIV/68407700:21230/17:00311768

Result on the web

<a href="http://dx.doi.org/10.1126/science.aam6960" target="_blank" >http://dx.doi.org/10.1126/science.aam6960</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1126/science.aam6960" target="_blank" >10.1126/science.aam6960</a>

Result language

angličtina

Original language name

DeepStack: Expert-level artificial intelligence in heads-up no-limit poker

Original language description

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 is the quintessential game of imperfect information, and a longstanding 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&apos;em. The approach is theoretically sound and is shown to produce more difficult to exploit strategies than prior approaches.

Czech name

—

Czech description

—

Type

J_imp - Article in a specialist periodical, which is included in the Web of Science database

CEP classification

—

OECD FORD branch

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Project

—

Continuities

S - Specificky vyzkum na vysokych skolach

Publication year

2017

Confidentiality

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Name of the periodical

Science

ISSN

0036-8075

e-ISSN

—

Volume of the periodical

2017

Issue of the periodical within the volume

356

Country of publishing house

US - UNITED STATES

Number of pages

6

Pages from-to

508-513

UT code for WoS article

000400545700031

EID of the result in the Scopus database

2-s2.0-85014477370