how a computer finally beat pro poker players for the first time by refining its intuition
Last Updated : GMT 06:49:16
Arab Today, arab today
Arab Today, arab today
Last Updated : GMT 06:49:16
Arab Today, arab today

How a computer finally beat pro poker players for the first time by refining its intuition

Arab Today, arab today

Arab Today, arab today How a computer finally beat pro poker players for the first time by refining its intuition

A report in the journal Science describes how the DeepStack machine bested nearly a dozen poker players, who were asked to play a 3,000-hand match over a period of four weeks
Miami - AFP

 A computer has defeated professional poker players for the first time by refining its intuition of the game called heads-up no-limit Texas hold'em poker, marking a step forward for artificial intelligence, scientists said Thursday.

The computer program, named DeepStack, beat 11 professional poker players recruited by the International Federation of Poker in December 2016. 

The report in the journal Science describes how the machine bested nearly a dozen players, who were asked to play a 3,000-hand match over a period of four weeks.

"DeepStack beat each of the 11 players who finished their match, with only one outside the margin of statistical significance, making it the first computer program to beat professional players in heads-up no-limit Texas hold'em poker," said the study.

DeepStack won by bridging "the gap between approaches used for games of perfect information -- like those used in checkers, chess, and Go -- with those used for imperfect information games."

DeepStack developed a form of "'intuition' honed through deep learning to reassess its strategy with each decision," said the report.

- Imperfect games -

Imperfect games require reasoning, because players are unaware of at least some of the others players' moves. 

"Poker has been a longstanding challenge problem in artificial intelligence," said principal investigator Michael Bowling, a professor in the University of Alberta's Faculty of Science.

"It is the quintessential game of imperfect information in the sense that the players don't have the same information or share the same perspective while they're playing."

Scientists who worked on the program came from the University of Alberta in Canada, Charles University in Prague and Czech Technical University.

DeepStack relies on a technique called continual re-solving, which allows the program to determine the correct strategy for a particular poker situation but does not force it to "think" about the entire game.

"We train our system to learn the value of situations," said Bowling. 

"Each situation itself is a mini poker game. Instead of solving one big poker game, it solves millions of these little poker games, each one helping the system to refine its intuition of how the game of poker works."

Despite the complexity of the game, DeepStack needs only three seconds of "thinking" time on average.

Bowling became the head of the University of Alberta's Computer Poker Research Group in 2006.

He and colleagues developed Polaris in 2008, beating top poker players at heads-up limit Texas hold'em poker, a variant of the game which limits the bets and raises players can make.

Next, they solved heads-up limit hold'em with Cepheus, a feat described in the journal Science in 2015.

A competing team of scientists at Carnegie Mellon University managed to beat four of the world's best human players in January in heads-up, no-limit Texas hold'em with its program, Libratus.

"The best AI's (artificial intelligence's) ability to do strategic reasoning with imperfect information has now surpassed that of the best humans," said Tuomas Sandholm, professor of computer science at Carnegie Mellon, at the time.

source: AFP

arabstoday
arabstoday

Name *

E-mail *

Comment Title*

Comment *

: Characters Left

Mandatory *

Terms of use

Publishing Terms: Not to offend the author, or to persons or sanctities or attacking religions or divine self. And stay away from sectarian and racial incitement and insults.

I agree with the Terms of Use

Security Code*

how a computer finally beat pro poker players for the first time by refining its intuition how a computer finally beat pro poker players for the first time by refining its intuition

 



Name *

E-mail *

Comment Title*

Comment *

: Characters Left

Mandatory *

Terms of use

Publishing Terms: Not to offend the author, or to persons or sanctities or attacking religions or divine self. And stay away from sectarian and racial incitement and insults.

I agree with the Terms of Use

Security Code*

how a computer finally beat pro poker players for the first time by refining its intuition how a computer finally beat pro poker players for the first time by refining its intuition

 



GMT 15:36 2017 Monday ,09 January

Major EU-GCC meeting in Riyadh today

GMT 17:19 2016 Thursday ,22 December

KFMC surgeons remove 28 kg tumor from woman’s uterus

GMT 17:33 2017 Wednesday ,16 August

Damac reports decline in property development sales

GMT 09:16 2018 Monday ,01 January

Seoul leaning towards military measures

GMT 01:05 2017 Wednesday ,20 December

No guarantees on French-German initiative on Ukraine

GMT 21:00 2017 Sunday ,17 September

Saif bin Zayed approves adoption of 'Emirati Reader'

GMT 02:10 2017 Thursday ,05 January

Bahrain Stock Index Drops 3.47 Points

GMT 02:05 2017 Thursday ,28 September

July24th-August23rd

GMT 04:17 2017 Saturday ,11 November

Laulala out to prove All Blacks worth against France

GMT 02:42 2017 Friday ,14 July

NATO Tripoli strike kills civilians

GMT 05:47 2017 Wednesday ,18 January

Mohamed bin Zayed attends opening of ADSW 2017

GMT 05:40 2016 Saturday ,26 November

Oil falls 2% on OPEC cut uncertainty

GMT 16:48 2016 Tuesday ,11 October

Greek police escort refugee children to school

GMT 09:42 2017 Saturday ,12 August

Prince Charles Promoted to Highest Military Rank

GMT 13:07 2017 Monday ,25 September

Iran blocks all Iraqi Kurdistan flights
Arab Today, arab today
 
 Arab Today Facebook,arab today facebook  Arab Today Twitter,arab today twitter Arab Today Rss,arab today rss  Arab Today Youtube,arab today youtube  Arab Today Youtube,arab today youtube

Maintained and developed by Arabs Today Group SAL.
All rights reserved to Arab Today Media Group 2021 ©

Maintained and developed by Arabs Today Group SAL.
All rights reserved to Arab Today Media Group 2021 ©

arabstoday arabstoday arabstoday arabstoday
arabstoday arabstoday arabstoday
arabstoday
بناية النخيل - رأس النبع _ خلف السفارة الفرنسية _بيروت - لبنان
arabstoday, Arabstoday, Arabstoday