NeurIPS 2017poster107 citations
Improving Regret Bounds for Combinatorial Semi-Bandits with Probabilistically Triggered Arms and Its Applications
Abstract
We study combinatorial multi-armed bandit with probabilistically triggered arms (CMAB-T) and semi-bandit feedback. We resolve a serious issue in the prior CMAB-T studies where the regret bounds contain a possibly exponentially large factor of 1/p
BibTeX
@inproceedings{NIPS2017_a8e864d0,
author = {Wang, Qinshi and Chen, Wei},
booktitle = {Advances in Neural Information Processing Systems},
editor = {I. Guyon and U. Von Luxburg and S. Bengio and H. Wallach and R. Fergus and S. Vishwanathan and R. Garnett},
pages = {},
publisher = {Curran Associates, Inc.},
title = {Improving Regret Bounds for Combinatorial Semi-Bandits with Probabilistically Triggered Arms and Its Applications},
url = {https://proceedings.neurips.cc/paper_files/paper/2017/file/a8e864d04c95572d1aece099af852d0a-Paper.pdf},
volume = {30},
year = {2017}
}