Resourceful Contextual Bandits
Abstract
We study contextual bandits with ancillary constraints on resources, which are common in real-world applications such as choosing ads or dynamic pricing of items. We design the first algorithm for solving these problems that handles constrained resources other than time, and improves over a trivial reduction to the non-contextual case. We consider very general settings for both contextual bandits (arbitrary policy sets, e.g. Dudik et al. (UAI'11)) and bandits with resource constraints (bandits with knapsacks, Badanidiyuru et al. (FOCS'13)), and prove a regret guarantee with near-optimal statistical properties.
Cite
@article{arxiv.1402.6779,
title = {Resourceful Contextual Bandits},
author = {Ashwinkumar Badanidiyuru and John Langford and Aleksandrs Slivkins},
journal= {arXiv preprint arXiv:1402.6779},
year = {2015}
}
Comments
This is the full version of a paper in COLT 2014. Version history: (v2) Added some details to one of the proofs, (v3) a big revision following comments from COLT reviewers (but no new results), (v4) edits in related work, minor edits elsewhere. (v6) A correction for Theorem 3, corollary for contextual dynamic pricing with discretization; updated follow-up work & open questions