论文信息 - Adaptive treatment allocation and the multi-armed bandit problem - 字舞流文

Adaptive treatment allocation and the multi-armed bandit problem

On propose une classe de regles d'allocation adaptative simples qui sont basees sur certaines limites de confiance superieures developpees a partir de la theorie du passage a la frontiere

[1] Dorian Feldman. Contributions to the "Two-Armed Bandit" Problem , 1962 .

[2] Herman Chernoff,et al. A Bayes Sequential Sampling Inspection Plan , 1965 .

[3] L. A. Klimko,et al. Bayesian rules for the two-armed bandit problem , 1977 .

[4] J. Gittins. Bandit processes and dynamic allocation indices , 1979 .

[5] H. Robbins,et al. Asymptotically efficient adaptive allocation rules , 1985 .

[6] Patchigolla Kiran Kumar,et al. A Survey of Some Results in Stochastic Adaptive Control , 1985 .

[7] Herman Chernoff,et al. Numerical solutions for Bayes sequential decision problems , 1986 .

[8] Tze Leung Lai,et al. Boundary crossing problems for sample means , 1988 .