Optimal Adaptive Policies for Sequential
β
Apostolos N. Burnetas; Michael N. Katehakis
π
Article
π
1996
π
Elsevier Science
π
English
β 301 KB
Consider the problem of sequential sampling from m statistical populations to maximize the expected sum of outcomes in the long run. Under suitable assumptions on the unknown parameters g β°, it is shown that there exists a class C of R Ε½ . adaptive policies with the following properties: i The expec