Asymptotically Optimal Strategies for Combinatorial Semi-Bandits in Polynomial Time
Abstract
We consider combinatorial semi-bandits with uncorrelated Gaussian rewards. In this article, we propose the first method, to the best of our knowledge, that enables to compute the solution of the Graves-Lai optimization problem in polynomial time for many combinatorial structures of interest. In turn, this immediately yields the first known approach to implement asymptotically optimal algorithms in polynomial time for combinatorial semi-bandits.
Cite
Text
Cuvelier et al. "Asymptotically Optimal Strategies for Combinatorial Semi-Bandits in Polynomial Time." Proceedings of the 32nd International Conference on Algorithmic Learning Theory, 2021.Markdown
[Cuvelier et al. "Asymptotically Optimal Strategies for Combinatorial Semi-Bandits in Polynomial Time." Proceedings of the 32nd International Conference on Algorithmic Learning Theory, 2021.](https://mlanthology.org/alt/2021/cuvelier2021alt-asymptotically/)BibTeX
@inproceedings{cuvelier2021alt-asymptotically,
title = {{Asymptotically Optimal Strategies for Combinatorial Semi-Bandits in Polynomial Time}},
author = {Cuvelier, Thibaut and Combes, Richard and Gourdin, Eric},
booktitle = {Proceedings of the 32nd International Conference on Algorithmic Learning Theory},
year = {2021},
pages = {505-528},
volume = {132},
url = {https://mlanthology.org/alt/2021/cuvelier2021alt-asymptotically/}
}