Utility-based Dueling Bandits as a Partial Monitoring Game
Abstract
Partial monitoring is a generic framework for sequential decision-making with incomplete feedback. It encompasses a wide class of problems such as dueling bandits, learning with expect advice, dynamic pricing, dark pools, and label efficient prediction. We study the utility-based dueling bandit problem as an instance of partial monitoring problem and prove that it fits the time-regret partial monitoring hierarchy as an easy - i.e. Theta (sqrt{T})- instance. We survey some partial monitoring algorithms and see how they could be used to solve dueling bandits efficiently. Keywords: Online learning, Dueling Bandits, Partial Monitoring, Partial Feedback, Multiarmed Bandits
Keywords
Cite
@article{arxiv.1507.02750,
title = {Utility-based Dueling Bandits as a Partial Monitoring Game},
author = {Pratik Gajane and Tanguy Urvoy},
journal= {arXiv preprint arXiv:1507.02750},
year = {2024}
}
Comments
Accepted at the 12th European Workshop on Reinforcement Learning (EWRL 2015)