Monotone multi-armed bandit allocations

Aleksandrs Slivkins
Proceedings of the 24th Annual Conference on Learning Theory, PMLR 19:829-834, 2011.

Abstract

We present a novel angle for multi-armed bandits (henceforth abbreviated MAB) which follows from the recent work on MAB mechanisms (Babaioff et al., 2009; Devanur and Kakade, 2009; Babaioff et al., 2010). The new problem is, essentially, about designing MAB algorithms under an additional constraint motivated by their application to MAB mechanisms. This note is self-contained, although some familiarity with MAB is assumed; we refer the reader to Cesa-Bianchi and Lugosi (2006) for more background.

Cite this Paper

BibTeX
@InProceedings{pmlr-v19-slivkins11b, title = {Monotone multi-armed bandit allocations}, author = {Slivkins, Aleksandrs}, booktitle = {Proceedings of the 24th Annual Conference on Learning Theory}, pages = {829--834}, year = {2011}, editor = {Kakade, Sham M. and von Luxburg, Ulrike}, volume = {19}, series = {Proceedings of Machine Learning Research}, address = {Budapest, Hungary}, month = {09--11 Jun}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v19/slivkins11b/slivkins11b.pdf}, url = {https://proceedings.mlr.press/v19/slivkins11b.html}, abstract = {We present a novel angle for multi-armed bandits (henceforth abbreviated MAB) which follows from the recent work on MAB mechanisms (Babaioff et al., 2009; Devanur and Kakade, 2009; Babaioff et al., 2010). The new problem is, essentially, about designing MAB algorithms under an additional constraint motivated by their application to MAB mechanisms. This note is self-contained, although some familiarity with MAB is assumed; we refer the reader to Cesa-Bianchi and Lugosi (2006) for more background.} }
Endnote
%0 Conference Paper %T Monotone multi-armed bandit allocations %A Aleksandrs Slivkins %B Proceedings of the 24th Annual Conference on Learning Theory %C Proceedings of Machine Learning Research %D 2011 %E Sham M. Kakade %E Ulrike von Luxburg %F pmlr-v19-slivkins11b %I PMLR %P 829--834 %U https://proceedings.mlr.press/v19/slivkins11b.html %V 19 %X We present a novel angle for multi-armed bandits (henceforth abbreviated MAB) which follows from the recent work on MAB mechanisms (Babaioff et al., 2009; Devanur and Kakade, 2009; Babaioff et al., 2010). The new problem is, essentially, about designing MAB algorithms under an additional constraint motivated by their application to MAB mechanisms. This note is self-contained, although some familiarity with MAB is assumed; we refer the reader to Cesa-Bianchi and Lugosi (2006) for more background.
RIS
TY - CPAPER TI - Monotone multi-armed bandit allocations AU - Aleksandrs Slivkins BT - Proceedings of the 24th Annual Conference on Learning Theory DA - 2011/12/21 ED - Sham M. Kakade ED - Ulrike von Luxburg ID - pmlr-v19-slivkins11b PB - PMLR DP - Proceedings of Machine Learning Research VL - 19 SP - 829 EP - 834 L1 - http://proceedings.mlr.press/v19/slivkins11b/slivkins11b.pdf UR - https://proceedings.mlr.press/v19/slivkins11b.html AB - We present a novel angle for multi-armed bandits (henceforth abbreviated MAB) which follows from the recent work on MAB mechanisms (Babaioff et al., 2009; Devanur and Kakade, 2009; Babaioff et al., 2010). The new problem is, essentially, about designing MAB algorithms under an additional constraint motivated by their application to MAB mechanisms. This note is self-contained, although some familiarity with MAB is assumed; we refer the reader to Cesa-Bianchi and Lugosi (2006) for more background. ER -
APA
Slivkins, A.. (2011). Monotone multi-armed bandit allocations. Proceedings of the 24th Annual Conference on Learning Theory, in Proceedings of Machine Learning Research 19:829-834 Available from https://proceedings.mlr.press/v19/slivkins11b.html.

Related Material