Geodesic
On nearly selfoptimizing strategies for multiarmed bandit problems with controlled arms
Applicationes Mathematicae, Tome 23 (1996) no. 4, pp. 449-473.

Voir la notice de l'article provenant de la source Institute of Mathematics Polish Academy of Sciences

Two kinds of strategies for a multiarmed Markov bandit problem with controlled arms are considered: a strategy with forcing and a strategy with randomization. The choice of arm and control function in both cases is based on the current value of the average cost per unit time functional. Some simulation results are also presented.
DOI : 10.4064/am-23-4-449-473
Keywords: selfoptimizing strategies, adaptative control, invariant measure, multiarmed bandit, stochastic control

Ewa Drabik 1

1 
@article{10_4064_am_23_4_449_473,
     author = {Ewa Drabik},
     title = {On nearly selfoptimizing strategies for multiarmed bandit problems with controlled arms},
     journal = {Applicationes Mathematicae},
     pages = {449--473},
     publisher = {mathdoc},
     volume = {23},
     number = {4},
     year = {1996},
     doi = {10.4064/am-23-4-449-473},
     zbl = {0848.93068},
     language = {en},
     url = {http://geodesic.mathdoc.fr/articles/10.4064/am-23-4-449-473/}
}
TY  - JOUR
AU  - Ewa Drabik
TI  - On nearly selfoptimizing strategies for multiarmed bandit problems with controlled arms
JO  - Applicationes Mathematicae
PY  - 1996
SP  - 449
EP  - 473
VL  - 23
IS  - 4
PB  - mathdoc
UR  - http://geodesic.mathdoc.fr/articles/10.4064/am-23-4-449-473/
DO  - 10.4064/am-23-4-449-473
LA  - en
ID  - 10_4064_am_23_4_449_473
ER  - 
%0 Journal Article
%A Ewa Drabik
%T On nearly selfoptimizing strategies for multiarmed bandit problems with controlled arms
%J Applicationes Mathematicae
%D 1996
%P 449-473
%V 23
%N 4
%I mathdoc
%U http://geodesic.mathdoc.fr/articles/10.4064/am-23-4-449-473/
%R 10.4064/am-23-4-449-473
%G en
%F 10_4064_am_23_4_449_473
Ewa Drabik. On nearly selfoptimizing strategies for multiarmed bandit problems with controlled arms. Applicationes Mathematicae, Tome 23 (1996) no. 4, pp. 449-473. doi : 10.4064/am-23-4-449-473. http://geodesic.mathdoc.fr/articles/10.4064/am-23-4-449-473/

Cité par Sources :