Artificial-intelligence program AlphaGo Zero trained in just days, without any human input.
This is a preview of subscription content, access via your institution
Access options
Access Nature and 54 other Nature Portfolio journals
Get Nature+, our best-value online-access subscription
$29.99 /Â 30Â days
cancel any time
Subscribe to this journal
Receive 51 print issues and online access
$199.00 per year
only $3.90 per issue
Buy this article
- Purchase on SpringerLink
- Instant access to full article PDF
Prices may be subject to local taxes which are calculated during checkout
References
Silver, D. et al. Nature 550, 354â359 (2017).
Singh, S., Okun, A. & Jackson, A. Nature 550, 336â337 (2017).
Related video
Discovering New KnowledgeDeepmind
Related links
Related links
Related links in Nature Research
Google reveals secret test of AI bot to beat top Go players 2017-Jan-04
Google's AI reasons its way around the London Underground 2016-Oct-13
What Googleâs winning Go algorithm will do next 2016-Mar-15
Google AI algorithm masters ancient game of Go 2016-Jan-27
Game-playing software holds lessons for neuroscience 2015-Feb-25
Rights and permissions
About this article
Cite this article
Gibney, E. Self-taught AI is best yet at strategy game Go. Nature (2017). https://doi.org/10.1038/nature.2017.22858
Published:
DOI: https://doi.org/10.1038/nature.2017.22858
This article is cited by
-
Rapid modeling of human-defined AI behavior patterns in games
Journal of Ambient Intelligence and Humanized Computing (2019)
-
All eyes are on AI
Nature Biomedical Engineering (2018)