@inproceedings{krishnamurthy2019contextual,
author = {Krishnamurthy, Akshay and Langford, John and Slivkins, Aleksandrs and Zhang, Chicheng},
title = {Contextual Bandits with Continuous Actions: Smoothing, Zooming, and Adapting},
booktitle = {Conference on Learning Theory},
year = {2019},
month = {June},
abstract = {We study contextual bandit learning with an abstract policy class and continuous action space. We obtain two qualitatively different regret bounds: one competes with a smoothed version of the policy class under no continuity assumptions, while the other requires standard Lipschitz assumptions. Both bounds exhibit data-dependent "zooming" behavior and, with no tuning, yield improved guarantees for benign problems. We also study adapting to unknown smoothness parameters, establishing a price-of-adaptivity and deriving optimal adaptive algorithms that require no additional information.},
url = {http://approjects.co.za/?big=en-us/research/publication/contextual-bandits-with-continuous-actions-smoothing-zooming-and-adapting/},
}