Anytime optimal algorithms in stochastic multi-armed bandits

Rémy Degenne, Vianney Perchet
Proceedings of The 33rd International Conference on Machine Learning, PMLR 48:1587-1595, 2016.

Abstract

We introduce an anytime algorithm for stochastic multi-armed bandit with optimal distribution free and distribution dependent bounds (for a specific family of parameters). The performances of this algorithm (as well as another one motivated by the conjectured optimal bound) are evaluated empirically. A similar analysis is provided with full information, to serve as a benchmark.

Cite this Paper

BibTeX
@InProceedings{pmlr-v48-degenne16, title = {Anytime optimal algorithms in stochastic multi-armed bandits}, author = {Degenne, Rémy and Perchet, Vianney}, booktitle = {Proceedings of The 33rd International Conference on Machine Learning}, pages = {1587--1595}, year = {2016}, editor = {Balcan, Maria Florina and Weinberger, Kilian Q.}, volume = {48}, series = {Proceedings of Machine Learning Research}, address = {New York, New York, USA}, month = {20--22 Jun}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v48/degenne16.pdf}, url = {https://proceedings.mlr.press/v48/degenne16.html}, abstract = {We introduce an anytime algorithm for stochastic multi-armed bandit with optimal distribution free and distribution dependent bounds (for a specific family of parameters). The performances of this algorithm (as well as another one motivated by the conjectured optimal bound) are evaluated empirically. A similar analysis is provided with full information, to serve as a benchmark.} }
Endnote
%0 Conference Paper %T Anytime optimal algorithms in stochastic multi-armed bandits %A Rémy Degenne %A Vianney Perchet %B Proceedings of The 33rd International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2016 %E Maria Florina Balcan %E Kilian Q. Weinberger %F pmlr-v48-degenne16 %I PMLR %P 1587--1595 %U https://proceedings.mlr.press/v48/degenne16.html %V 48 %X We introduce an anytime algorithm for stochastic multi-armed bandit with optimal distribution free and distribution dependent bounds (for a specific family of parameters). The performances of this algorithm (as well as another one motivated by the conjectured optimal bound) are evaluated empirically. A similar analysis is provided with full information, to serve as a benchmark.
RIS
TY - CPAPER TI - Anytime optimal algorithms in stochastic multi-armed bandits AU - Rémy Degenne AU - Vianney Perchet BT - Proceedings of The 33rd International Conference on Machine Learning DA - 2016/06/11 ED - Maria Florina Balcan ED - Kilian Q. Weinberger ID - pmlr-v48-degenne16 PB - PMLR DP - Proceedings of Machine Learning Research VL - 48 SP - 1587 EP - 1595 L1 - http://proceedings.mlr.press/v48/degenne16.pdf UR - https://proceedings.mlr.press/v48/degenne16.html AB - We introduce an anytime algorithm for stochastic multi-armed bandit with optimal distribution free and distribution dependent bounds (for a specific family of parameters). The performances of this algorithm (as well as another one motivated by the conjectured optimal bound) are evaluated empirically. A similar analysis is provided with full information, to serve as a benchmark. ER -
APA
Degenne, R. & Perchet, V.. (2016). Anytime optimal algorithms in stochastic multi-armed bandits. Proceedings of The 33rd International Conference on Machine Learning, in Proceedings of Machine Learning Research 48:1587-1595 Available from https://proceedings.mlr.press/v48/degenne16.html.

Related Material