Design of Experiments for Stochastic Contextual Linear Bandits
Andrea Zanette, Kefan Dong, Jonathan Lee, Emma Brunskill
Abstract
In the stochastic linear contextual bandit setting there exist several minimax procedures for exploration with policies that are reactive to the data being acquired. In practice, there can be a significant engineering overhead to deploy these algorithms, especially when the dataset is collected in a distributed fashion or when a human in the loop is needed to implement a different policy. Exploring with a single non-reactive policy is beneficial in such cases. Assuming some batch contexts are available, we design a single stochastic policy to collect a good dataset from which a near-optimal policy can be extracted. We present a theoretical analysis as well as numerical experiments on both synthetic and real-world datasets.
BibTeX
@inproceedings{
zanette2021design,
title={Design of Experiments for Stochastic Contextual Linear Bandits},
author={Andrea Zanette and Kefan Dong and Jonathan Lee and Emma Brunskill},
booktitle={Advances in Neural Information Processing Systems},
editor={A. Beygelzimer and Y. Dauphin and P. Liang and J. Wortman Vaughan},
year={2021},
url={https://openreview.net/forum?id=KsfuvGB3vco}
}