An algorithm with nearly optimal pseudo-regret for both stochastic and adversarial bandits
Publikationen: Beitrag in Buch/Bericht/Konferenzband › Beitrag in Konferenzband
Standard
An algorithm with nearly optimal pseudo-regret for both stochastic and adversarial bandits. / Auer, Peter; Chiang, Chao-Kai.
Proceedings of the 29th Conference on Learning Theory, COLT 2016. 2016. S. 116-120 (JMLR Workshop and Conference Proceedings; Band 49).
Proceedings of the 29th Conference on Learning Theory, COLT 2016. 2016. S. 116-120 (JMLR Workshop and Conference Proceedings; Band 49).
Publikationen: Beitrag in Buch/Bericht/Konferenzband › Beitrag in Konferenzband
Harvard
Auer, P & Chiang, C-K 2016, An algorithm with nearly optimal pseudo-regret for both stochastic and adversarial bandits. in Proceedings of the 29th Conference on Learning Theory, COLT 2016. JMLR Workshop and Conference Proceedings, Bd. 49, S. 116-120. <http://proceedings.mlr.press/v49/auer16.pdf>
APA
Auer, P., & Chiang, C.-K. (2016). An algorithm with nearly optimal pseudo-regret for both stochastic and adversarial bandits. In Proceedings of the 29th Conference on Learning Theory, COLT 2016 (S. 116-120). (JMLR Workshop and Conference Proceedings; Band 49). http://proceedings.mlr.press/v49/auer16.pdf
Vancouver
Auer P, Chiang CK. An algorithm with nearly optimal pseudo-regret for both stochastic and adversarial bandits. in Proceedings of the 29th Conference on Learning Theory, COLT 2016. 2016. S. 116-120. (JMLR Workshop and Conference Proceedings).
Author
Bibtex - Download
@inproceedings{6e79efa69ead4bdd9e3e670efd263458,
title = "An algorithm with nearly optimal pseudo-regret for both stochastic and adversarial bandits",
author = "Peter Auer and Chao-Kai Chiang",
year = "2016",
month = jun,
day = "23",
language = "English",
series = "JMLR Workshop and Conference Proceedings",
publisher = "JMLR.org",
pages = "116--120",
booktitle = "Proceedings of the 29th Conference on Learning Theory, COLT 2016",
}
RIS (suitable for import to EndNote) - Download
TY - GEN
T1 - An algorithm with nearly optimal pseudo-regret for both stochastic and adversarial bandits
AU - Auer, Peter
AU - Chiang, Chao-Kai
PY - 2016/6/23
Y1 - 2016/6/23
M3 - Conference contribution
T3 - JMLR Workshop and Conference Proceedings
SP - 116
EP - 120
BT - Proceedings of the 29th Conference on Learning Theory, COLT 2016
ER -
