We create a computationally tractable algorithm for contextual bandits with continuous actions having unknown structure. Our reduction-style algorithm composes with most supervised learning representations. We prove that it works in a general sense and verify the new functionality with large-scale experiments.
@article{arxiv.2006.06040,
title = {Efficient Contextual Bandits with Continuous Actions},
author = {Maryam Majzoubi and Chicheng Zhang and Rajan Chari and Akshay Krishnamurthy and John Langford and Aleksandrs Slivkins},
journal= {arXiv preprint arXiv:2006.06040},
year = {2020}
}