An asymptotically optimal policy for finite support models in the multiarmed bandit problem

ISSN： 0885-6125

Source： Machine Learning, Vol.85, Iss.3, 2011-12, pp. : 361-391

Disclaimer: Any content in publications that violate the sovereignty, the constitution or regulations of the PRC is not accepted or approved by CNPIEC.

Previous Menu Next

Abstract

Related content

Finite-time Analysis of the Multiarmed Bandit Problem

By Auer P.

Machine Learning, Vol. 47, Iss. 2-3, 2002-05 ,pp. : 235-256

Springer Publishing Company

Access to resources Recommend Favorite

The functions of finite support: a canonical learning problem

By Freivalds Rusins Kinber Efim Smith Carl H.

Journal of Experimental & Theoretical Artificial Intelligence, Vol. 11, Iss. 4, 1999-10 ,pp. : 543-552

Taylor & Francis Ltd

Access to resources Recommend Favorite

Priority index heuristic for multi-armed bandit problems with set-up costs and/or set-up time delays

By Dusonchet F. Hongler M.

International Journal of Computer Integrated Manufacturing, Vol. 19, Iss. 3, 2006-04 ,pp. : 210-219

Taylor & Francis Ltd

Access to resources Recommend Favorite

Asymptotically optimal perfect steganographic systems

By Ryabko B. Ryabko D.

Problems of Information Transmission, Vol. 45, Iss. 2, 2009-06 ,pp. : 184-190

MAIK Nauka/Interperiodica

Access to resources Recommend Favorite

Asymptotically optimal control of parallel tandem queues with loss

By Sheu Ru-Shuo Ziedins Ilze

Queueing Systems, Vol. 65, Iss. 3, 2010-07 ,pp. : 211-227

Springer Publishing Company

Access to resources Recommend Favorite