Shipra Agrawal, Nikhil R. Devanur, Lihong Li. An efficient algorithm for contextual bandits with knapsacks, and an extension to concave objectives. In Vitaly Feldman, Alexander Rakhlin, Ohad Shamir, editors, Proceedings of the 29th Conference on Learning Theory, COLT 2016, New York, USA, June 23-26, 2016. Volume 49 of JMLR Workshop and Conference Proceedings, pages 4-18, JMLR.org, 2016. [doi]
@inproceedings{AgrawalDL16-0,
title = {An efficient algorithm for contextual bandits with knapsacks, and an extension to concave objectives},
author = {Shipra Agrawal and Nikhil R. Devanur and Lihong Li},
year = {2016},
url = {http://jmlr.org/proceedings/papers/v49/agrawal16.html},
researchr = {https://researchr.org/publication/AgrawalDL16-0},
cites = {0},
citedby = {0},
pages = {4-18},
booktitle = {Proceedings of the 29th Conference on Learning Theory, COLT 2016, New York, USA, June 23-26, 2016},
editor = {Vitaly Feldman and Alexander Rakhlin and Ohad Shamir},
volume = {49},
series = {JMLR Workshop and Conference Proceedings},
publisher = {JMLR.org},
}