Multi-armed bandits in discrete and continuous time
Kaspi, Haya ; Mandelbaum, Avishai
Ann. Appl. Probab., Tome 8 (1998) no. 1, p. 1270-1290 / Harvested from Project Euclid
Text on Project Euclid
PDF
Alt PDF
We analyze Gittins' Markovian model, as generalized by Varaiya, Walrand and Buyukkoc, in discrete and continuous time. The approach resembles Weber's modification of Whittle's, within the framework of both multi-parameter processes and excursion theory. It is shown that index-priority strategies are optimal, in concert with all the special cases that have been treated previously.
Publié le : 1998-11-14
Classification:  Multi-armed bandits,  optional increasing paths,  multiparameter processes,  excursions,  local times,  dual predictable projection,  60G40,  60J55,  60G44 
@article{1028903380,
     author = {Kaspi, Haya and Mandelbaum, Avishai},
     title = {Multi-armed bandits in discrete and continuous time},
     journal = {Ann. Appl. Probab.},
     volume = {8},
     number = {1},
     year = {1998},
     pages = { 1270-1290},
     language = {en},
     url = {http://dml.mathdoc.fr/item/1028903380}
}

Kaspi, Haya; Mandelbaum, Avishai. Multi-armed bandits in discrete and continuous time. Ann. Appl. Probab., Tome 8 (1998) no. 1, pp.  1270-1290. http://gdmltest.u-ga.fr/item/1028903380/