• Media type: E-Book
  • Title: Robust Control of the Multi-Armed Bandit Problem
  • Contributor: Caro, Felipe [Author]; Das Gupta, Aparupa [Other]
  • Published: [S.l.]: SSRN, [2014]
  • Extent: 1 Online-Ressource (21 p)
  • Language: English
  • DOI: 10.2139/ssrn.2326583
  • Identifier:
  • Origination:
  • Footnote: Nach Informationen von SSRN wurde die ursprüngliche Fassung des Dokuments July 1, 2014 erstellt
  • Description: We study a robust model of the multi-armed bandit (MAB) problem in which the transition probabilities are ambiguous and belong to subsets of the probability simplex. We characterize the optimal policy as a project-by-project retirement policy but we show that arms become dependent so the Gittins index is not optimal. We propose a Lagrangian index policy that is computationally equivalent to evaluating the indices of a non-robust MAB. For a project selection problem we fi nd that it performs near optimal
  • Access State: Open Access