Elad Hazan, Satyen Kale. A simple multi-armed bandit algorithm with optimal variation-bounded regret. Journal of Machine Learning Research, 19:817-820, 2011. [doi]
@article{HazanK11b,
title = {A simple multi-armed bandit algorithm with optimal variation-bounded regret},
author = {Elad Hazan and Satyen Kale},
year = {2011},
url = {http://www.jmlr.org/proceedings/papers/v19/hazan11b/hazan11b.pdf},
researchr = {https://researchr.org/publication/HazanK11b},
cites = {0},
citedby = {0},
journal = {Journal of Machine Learning Research},
volume = {19},
pages = {817-820},
}