Randomization in the Two-Armed Bandit Problem
Dalang, Robert C.
Ann. Probab., Tome 18 (1990) no. 4, p. 218-225 / Harvested from Project Euclid
Text on Project Euclid
PDF
Alt PDF
We give a short new proof of the existence of optimal solutions to a continuous time formulation of the two-armed bandit problem, using a new topological embedding of the set of randomized optional increasing paths. We do not make any hypothesis on the two-parameter filtration, other than completeness and right-continuity.
Publié le : 1990-01-14
Classification:  Two-parameter process,  two-armed bandit,  stochastic control,  randomization,  60G40,  93E20 
@article{1176990946,
     author = {Dalang, Robert C.},
     title = {Randomization in the Two-Armed Bandit Problem},
     journal = {Ann. Probab.},
     volume = {18},
     number = {4},
     year = {1990},
     pages = { 218-225},
     language = {en},
     url = {http://dml.mathdoc.fr/item/1176990946}
}

Dalang, Robert C. Randomization in the Two-Armed Bandit Problem. Ann. Probab., Tome 18 (1990) no. 4, pp.  218-225. http://gdmltest.u-ga.fr/item/1176990946/