News & Views | Published:

Artificial intelligence

Learning to see and act

Nature volume 518, pages 486487 (26 February 2015) | Download Citation

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

Access optionsAccess options

Rent or Buy article

Get time limited or full article access on ReadCube.

from$8.99

All prices are NET prices.

References

  1. 1.

    et al. Nature 518, 529–533 (2015).

  2. 2.

    & Reinforcement Learning: An Introduction (MIT Press, 1998).

  3. 3.

    Learning from Delayed Rewards. PhD thesis, Univ. Cambridge (1989).

  4. 4.

    , , , & Adv. Neural Inf. Process. Syst. 27 (2014).

  5. 5.

    & in Proc. 25th AAAI Conf. on Artificial Intelligence 100–108 (2011).

  6. 6.

    et al. in Proc. 29th Int. Conf. on Machine Learning 1255–1262 (Omnipress, 2012).

Download references

Author information

Affiliations

  1. Bernhard Schölkopf is at the Max Planck Institute for Intelligent Systems, 72076 Tübingen, Germany.

    • Bernhard Schölkopf

Authors

  1. Search for Bernhard Schölkopf in:

Corresponding author

Correspondence to Bernhard Schölkopf.

About this article

Publication history

Published

DOI

https://doi.org/10.1038/518486a

Comments

By submitting a comment you agree to abide by our Terms and Community Guidelines. If you find something abusive or that does not comply with our terms or guidelines please flag it as inappropriate.

Newsletter Get the most important science stories of the day, free in your inbox. Sign up for Nature Briefing