Abstract.
A radically new approach to indexable systems pioneered by Bertsimas and Niño-Mora is utilised to provide novel analyses of classes of complex multi-armed bandits in which the individual bandits have their own decision structure. A new index result for an undiscounted model is established. Parallel server versions of the models are studied via (the dual of) an LP relaxation. This analysis yields a natural heuristic policy which is evaluated numerically.
Similar content being viewed by others
Author information
Authors and Affiliations
Additional information
Received March 1997/Revised version April 1998
Rights and permissions
About this article
Cite this article
Garbe, R., Glazebrook, K. On a new approach to the analysis of complex multi-armed bandits. Mathematical Methods of OR 48, 419–442 (1998). https://doi.org/10.1007/s001860050036
Issue Date:
DOI: https://doi.org/10.1007/s001860050036