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
Notes
References
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).
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Schölkopf, B. Learning to see and act. Nature 518, 486–487 (2015). https://doi.org/10.1038/518486a
Published:
Issue Date:
DOI: https://doi.org/10.1038/518486a
- Springer Nature Limited
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)
-
Transferring policy of deep reinforcement learning from simulation to reality for robotics
Nature Machine Intelligence (2022)
-
Self-organizing maps of typhoon tracks allow for flood forecasts up to two days in advance
Nature Communications (2020)
-
Artificial neural networks enabled by nanophotonics
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)