Multi-Armed Bandits and the Gittins Index
Journal of the Royal Statistical Society: Series B (Statistical Methodology) · 1980 · Volume 42 · Issue 2
DOI: 10.1111/j.2517-6161.1980.tb01111.x
Abstract
A plausible conjecture (C) has the implication that a relationship (12) holds between the maximal expected rewards for a multi-project process and for a one-project process (Fand φirespectively), if the option of retirement with reward M is available. The validity of this relation and optimality of Gittins' index rule are verified simultaneously by dynamic programming methods. These results are partially extended to the case of so-called “bandit superprocesses”.
Keywords
bandit processes, dynamic allocation indices, two-armed bandit problem, optimal resource allocation
Enable JavaScript for citation tools and additional paper interactions.