Asymptotically optimal algorithms for budgeted multiple play bandits.

Authors
Publication date
2019
Publication type
Journal Article
Summary We study a generalization of the multi-armed bandit problem with multiple plays where there is a cost associated with pulling each arm and the agent has a budget at each time that dictates how much she can expect to spend. We derive an asymptotic regret lower bound for any uniformly efficient algorithm in our setting. We then study a variant of Thompson sampling for Bernoulli rewards and a variant of KL-UCB for both single-parameter exponential families and bounded, finitely supported rewards. We show these algorithms are asymptotically optimal, both in rate and leading problem-dependent constants, including in the thick margin setting where multiple arms fall on the decision boundary.
Publisher
Springer Science and Business Media LLC
Topics of the publication
  • ...
  • No themes identified
Themes detected by scanR from retrieved publications. For more information, see https://scanr.enseignementsup-recherche.gouv.fr