Skip to main content

Taming the Monster: A Fast and Simple Algorithm for Contextual Bandits

Author(s): Agarwal, Alekh; Hsu, Daniel; Kale, Satyen; Langford, John; Li, Lihong; et al

To refer to this page use:
Abstract: We present a new algorithm for the contextual bandit learning problem, where the learner repeatedly takes one of $K$ actions in response to the observed context, and observes the reward only for that chosen action. Our method assumes access to an oracle for solving fully supervised cost-sensitive classification problems and achieves the statistically optimal regret guarantee with only $\tilde{O}(\sqrt{KT/\log N})$ oracle calls across all $T$ rounds, where $N$ is the number of policies in the policy class we compete against. By doing so, we obtain the most practical contextual bandit learning algorithm amongst approaches that work for general policy classes. We further conduct a proof-of-concept experiment which demonstrates the excellent computational and prediction performance of (an online variant of) our algorithm relative to several baselines.
Publication Date: 2014
Citation: Agarwal, Alekh, Hsu, Daniel, Kale, Satyen, Langford, John, Li, Lihong, Schapire, Robert E. (Taming the Monster: A Fast and Simple Algorithm for Contextual Bandits
Type of Material: Conference Article
Journal/Proceeding Title: 31st International Conference on Machine Learning
Version: Author's manuscript

Items in OAR@Princeton are protected by copyright, with all rights reserved, unless otherwise indicated.