Reinforcement learning improves behaviour from evaluative feedback
Crossref DOI link: https://doi.org/10.1038/nature14540
Published Online: 2015-05-27
Published Print: 2015-05-28
Update policy: https://doi.org/10.1007/springer_crossmark_policy
Littman, Michael L.
Text and Data Mining valid from 2015-05-27
Version of Record valid from 2015-05-27
Article History
Received: 11 January 2015
Accepted: 28 April 2015
First Online: 27 May 2015
Competing interests
: The author declares no competing financial interests.