A simple multi-armed bandit algorithm with optimal variation-bounded regret

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]

Authors

Elad Hazan

This author has not been identified. Look up 'Elad Hazan' in Google

Satyen Kale

This author has not been identified. Look up 'Satyen Kale' in Google