DMCA
On optimal foraging and multi-armed bandits (2013)
| Venue: | in Proc. 51st Annu. Allerton Conf. Commun. Control Comput |
| Citations: | 4 - 3 self |
BibTeX
@INPROCEEDINGS{Srivastava13onoptimal,
author = {Vaibhav Srivastava and Paul Reverdy and Naomi E. Leonard},
title = {On optimal foraging and multi-armed bandits},
booktitle = {in Proc. 51st Annu. Allerton Conf. Commun. Control Comput},
year = {2013},
pages = {494--499}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
Abstract—We consider two variants of the standard multi-armed bandit problem, namely, the multi-armed bandit prob-lem with transition costs and the multi-armed bandit problem on graphs. We develop block allocation algorithms for these problems that achieve an expected cumulative regret that is uniformly dominated by a logarithmic function of time, and an expected cumulative number of transitions from one arm to another arm uniformly dominated by a double-logarithmic function of time. We observe that the multi-armed bandit prob-lem with transition costs and the associated block allocation algorithm capture the key features of popular animal foraging models in literature. I.
Keyphrases
multi-armed bandit optimal foraging multi-armed bandit prob-lem transition cost double-logarithmic function block allocation algorithm expected cumulative number multi-armed bandit problem logarithmic function associated block allocation algorithm capture standard multi-armed bandit problem key feature expected cumulative regret popular animal
