AlphaGo

E39541

Go-playing program artificial intelligence system computer program

AlphaGo is an artificial intelligence program developed by DeepMind that became famous for defeating world champion Go players using deep neural networks and reinforcement learning.

Jump to: Surface forms Statements Referenced by

Observed surface forms (6)

Surface form	Occurrences
AlphaGo Master	2
AlphaGo Fan	1
AlphaGo Lee	1
AlphaGo match against Lee Sedol	1
AlphaGo project	1
Mastering the game of Go with deep neural networks and tree search	1

Statements (53)

Predicate	Object
instanceOf	Go-playing program ⓘ artificial intelligence system ⓘ computer program ⓘ
alsoKnownAs	AlphaGo Fan ⓘ AlphaGo ⓘ surface form: AlphaGo Lee AlphaGo ⓘ surface form: AlphaGo Master
basedOn	deep learning ⓘ machine learning ⓘ policy networks ⓘ value networks ⓘ
boardGame	Go ⓘ
countryOfOrigin	United Kingdom ⓘ
developer	DeepMind ⓘ DeepMind ⓘ surface form: Google DeepMind
field	artificial intelligence research ⓘ computer Go ⓘ
firstReleaseYear	2015 ⓘ
genre	board game AI ⓘ
governingBodyInMatch	Chinese Weiqi Association ⓘ Korea Baduk Association ⓘ
inspired	AlphaZero ⓘ surface form: AlphaGo Zero AlphaZero ⓘ MuZero ⓘ
matchDate	2015-10 ⓘ 2016-03 ⓘ 2017-05 ⓘ
matchLocation	London, England ⓘ surface form: London Seoul ⓘ Wuzhen ⓘ
notableAchievement	defeated European Go champion Fan Hui 5–0 in October 2015 ⓘ defeated Ke Jie 3–0 in May 2017 ⓘ defeated world champion Lee Sedol 4–1 in March 2016 ⓘ first computer program to defeat a professional Go player on a full-sized 19x19 board without handicaps ⓘ
notableImpact	demonstrated the power of deep reinforcement learning in complex board games ⓘ
notableWork	AlphaGo self-linksurface differs ⓘ surface form: AlphaGo Fan Lee Sedol ⓘ surface form: AlphaGo Lee AlphaGo self-linksurface differs ⓘ surface form: AlphaGo Master
operatingSystem	Linux ⓘ
opponent	Fan Hui ⓘ Ke Jie ⓘ Lee Sedol ⓘ
parentOrganizationOfDeveloper	Google ⓘ
programmingLanguage	C++ ⓘ Python ⓘ
sponsor	Google ⓘ
successor	AlphaZero ⓘ surface form: AlphaGo Zero AlphaZero ⓘ MuZero ⓘ
trainingMethod	reinforcement learning through self-play ⓘ supervised learning from human expert games ⓘ
uses	Monte Carlo tree search ⓘ deep neural networks ⓘ reinforcement learning ⓘ

Referenced by (13)

Full triples — surface form annotated when it differs from this entity's canonical label.

AlphaGo → alsoKnownAs → AlphaGo ⓘ

this entity surface form: AlphaGo Lee

AlphaGo → alsoKnownAs → AlphaGo ⓘ

this entity surface form: AlphaGo Master

DeepMind → developed → AlphaGo ⓘ

MuZero → inspiredBy → AlphaGo ⓘ

DeepMind → knownFor → AlphaGo ⓘ

Demis Hassabis → knownFor → AlphaGo ⓘ

David Silver → notablePaper → AlphaGo ⓘ

this entity surface form: Mastering the game of Go with deep neural networks and tree search

DeepMind → notableProject → AlphaGo ⓘ

this entity surface form: AlphaGo match against Lee Sedol

AlphaGo → notableWork → AlphaGo self-linksurface differs ⓘ

this entity surface form: AlphaGo Fan

AlphaGo → notableWork → AlphaGo self-linksurface differs ⓘ

this entity surface form: AlphaGo Master

David Silver → notableWork → AlphaGo ⓘ

AlphaZero → parentProject → AlphaGo ⓘ

this entity surface form: AlphaGo project

AlphaStar → relatedTo → AlphaGo ⓘ