Ofer Dekel, Ambuj Tewari, Raman Arora
Online Bandit Learning against an Adaptive Adversary: from Regret to Policy Regret
ICML, 2012.
@inproceedings{ICML-2012-DekelTA,
author = "Ofer Dekel and Ambuj Tewari and Raman Arora",
booktitle = "{Proceedings of the 29th International Conference on Machine Learning}",
ee = "http://icml.cc/2012/papers/749.pdf",
pages = "227",
publisher = "{icml.cc / Omnipress}",
title = "{Online Bandit Learning against an Adaptive Adversary: from Regret to Policy Regret}",
year = 2012,
}