Mastering the game of Go without human knowledge

A long-standing goal of artificial intelligence is an algorithm that learns, tabula rasa , superhuman proficiency in challenging domains. Recently, AlphaGo became the first program to defeat a world champion in the game of Go. The tree search in AlphaGo evaluated positions and selected moves using d...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	Nature (London) Jg. 550; H. 7676; S. 354 - 359
Hauptverfasser:	Silver, David, Schrittwieser, Julian, Simonyan, Karen, Antonoglou, Ioannis, Huang, Aja, Guez, Arthur, Hubert, Thomas, Baker, Lucas, Lai, Matthew, Bolton, Adrian, Chen, Yutian, Lillicrap, Timothy, Hui, Fan, Sifre, Laurent, van den Driessche, George, Graepel, Thore, Hassabis, Demis
Format:	Journal Article
Sprache:	Englisch
Veröffentlicht:	London Nature Publishing Group UK 19.10.2017 Nature Publishing Group
Schlagworte:	631/378/1788 639/705/1042 639/705/117 Algorithms Artificial intelligence Artificial neural networks Computer games Forecasts and trends Games Games, Recreational Go (Game) Humanities and Social Sciences Humans Learning Machine learning Mastering multidisciplinary Neural networks Neural Networks (Computer) Probability Reinforcement Reinforcement (Psychology) Science Software Supervised Machine Learning Technology application Unsupervised Machine Learning
ISSN:	0028-0836, 1476-4687, 1476-4687
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Schreiben Sie den ersten Kommentar!