An artificial-intelligence system uses machine learning from massive training sets to teach itself to play 49 classic computer games, demonstrating that it can adapt to a variety of tasks. See Letter p.529
This is a preview of subscription content, access via your institution
Open Access articles citing this article.
Nature Communications Open Access 24 April 2020
Light: Science & Applications Open Access 08 May 2019
Subscribe to this journal
Receive 51 print issues and online access
$199.00 per year
only $3.90 per issue
Rent or buy this article
Prices vary by article type
Prices may be subject to local taxes which are calculated during checkout
Mnih, V. et al. Nature 518, 529–533 (2015).
Sutton R. S. & Barto A. G. Reinforcement Learning: An Introduction (MIT Press, 1998).
Watkins, C. J. C. H. Learning from Delayed Rewards. PhD thesis, Univ. Cambridge (1989).
Guo, X., Singh, S., Lee, H., Lewis, R. L. & Wang, X. Adv. Neural Inf. Process. Syst. 27 (2014).
Bareinboim, E. & Pearl, J. in Proc. 25th AAAI Conf. on Artificial Intelligence 100–108 (2011).
Schölkopf, B. et al. in Proc. 29th Int. Conf. on Machine Learning 1255–1262 (Omnipress, 2012).
About this article
Cite this article
Schölkopf, B. Learning to see and act. Nature 518, 486–487 (2015). https://doi.org/10.1038/518486a
This article is cited by
Quantification of intratumoural heterogeneity in mice and patients via machine-learning models trained on PET–MRI data
Nature Biomedical Engineering (2023)
Nature Machine Intelligence (2022)
Nature Communications (2020)
Light: Science & Applications (2019)
A reference framework and overall planning of industrial artificial intelligence (I-AI) for new application scenarios
The International Journal of Advanced Manufacturing Technology (2019)