Theory and Decision

, Volume 47, Issue 3, pp 267–295

Dynamic stochastic dominance in bandit decision problems

Authors

  • Thierry Magnac
    • INRA-LEA, École Normale supérieure
  • Jean-Marc Robin
    • INRA-LEA, École Normale supérieure
Article

DOI: 10.1023/A:1005142630173

Cite this article as:
Magnac, T. & Robin, J. Theory and Decision (1999) 47: 267. doi:10.1023/A:1005142630173

Abstract

The aim of this paper is to study the monotonicity properties with respect to the probability distribution of the state processes, of optimal decisions in bandit decision problems. Orderings of dynamic discrete projects are provided by extending the notion of stochastic dominance to stochastic processes.

Stochastic dynamic programingMulti-armed bandit problemsStochastic dominance

Copyright information

© Kluwer Academic Publishers 1999