@inproceedings{1de826d6f0a5499a9049b660c9afb1b6,
title = "Bandits with budgets",
abstract = "Motivated by online advertising applications, we consider a version of the classical multi-armed bandit problem where there is a cost associated with pulling each arm, and a corresponding budget which limits the number of times that an arm can be pulled. We derive regret bounds on the expected reward in such a bandit problem using a modification of the well-known upper confidence bound algorithm UCB1.",
author = "Chong Jiang and R. Srikant",
year = "2013",
doi = "10.1109/CDC.2013.6760730",
language = "English (US)",
isbn = "9781467357173",
series = "Proceedings of the IEEE Conference on Decision and Control",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "5345--5350",
booktitle = "2013 IEEE 52nd Annual Conference on Decision and Control, CDC 2013",
address = "United States",
note = "52nd IEEE Conference on Decision and Control, CDC 2013 ; Conference date: 10-12-2013 Through 13-12-2013",
}