Shipra Agrawal, Navin Goyal. Analysis of Thompson Sampling for the Multi-armed Bandit Problem. In Shie Mannor, Nathan Srebro, Robert C. Williamson, editors, COLT 2012 - The 25th Annual Conference on Learning Theory, June 25-27, 2012, Edinburgh, Scotland. JMLR.org, 2012. [doi]
@inproceedings{journals-jmlr-AgrawalG12,
title = {Analysis of Thompson Sampling for the Multi-armed Bandit Problem},
author = {Shipra Agrawal and Navin Goyal},
year = {2012},
url = {http://www.jmlr.org/proceedings/papers/v23/agrawal12/agrawal12.pdf},
researchr = {https://researchr.org/publication/journals-jmlr-AgrawalG12},
cites = {0},
citedby = {0},
booktitle = {COLT 2012 - The 25th Annual Conference on Learning Theory, June 25-27, 2012, Edinburgh, Scotland},
editor = {Shie Mannor and Nathan Srebro and Robert C. Williamson},
publisher = {JMLR.org},
}