Taming the Monster: A Fast and Simple Algorithm for Contextual Bandits
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 costsensitive 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 proofofconcept experiment which demonstrates the excellent computational and prediction performance of (an online variant of) our algorithm relative to several baselines.
 Publication:

arXiv eprints
 Pub Date:
 February 2014
 arXiv:
 arXiv:1402.0555
 Bibcode:
 2014arXiv1402.0555A
 Keywords:

 Computer Science  Machine Learning;
 Statistics  Machine Learning