Contributions to the "Two-Armed Bandit" Problem
Feldman, Dorian
Ann. Math. Statist., Tome 33 (1962) no. 4, p. 847-856 / Harvested from Project Euclid
The Bayes sequential design is obtained for an optimization problem involving the choice of experiments. Given are experiments $A, B$, densities $p_1, p_2$, a positive integer $N$ and a number $\xi \varepsilon \lbrack 0, 1\rbrack$. A sequence of $N$ observations is to be made such that at each stage either $A$ or $B$ is observed, the loss being 1 if the experiment with density $p_2$ is chosen, 0 otherwise. $\xi$ is the prior probability that $A$ has density $p_1$. If the mean of $p_1$ is bigger than the mean of $p_2$ one obtains a more common version of the "two-armed bandit" (see e.g. [1]). The principal result of this paper is a proof of optimality for the procedure which at each stage chooses the experiment with higher posterior probability of being correct. Some attention is also given to the problem of computing risk functions.
Publié le : 1962-09-14
Classification: 
@article{1177704454,
     author = {Feldman, Dorian},
     title = {Contributions to the "Two-Armed Bandit" Problem},
     journal = {Ann. Math. Statist.},
     volume = {33},
     number = {4},
     year = {1962},
     pages = { 847-856},
     language = {en},
     url = {http://dml.mathdoc.fr/item/1177704454}
}
Feldman, Dorian. Contributions to the "Two-Armed Bandit" Problem. Ann. Math. Statist., Tome 33 (1962) no. 4, pp.  847-856. http://gdmltest.u-ga.fr/item/1177704454/