Sciweavers

Share
113 search results - page 1 / 23
» Algorithm Selection as a Bandit Problem with Unbounded Losse...
Sort
View
LION
2010
Springer
190views Optimization» more  LION 2010»
8 years 10 months ago
Algorithm Selection as a Bandit Problem with Unbounded Losses
Abstract. Algorithm selection is typically based on models of algorithm performance learned during a separate offline training sequence, which can be prohibitively expensive. In r...
Matteo Gagliolo, Jürgen Schmidhuber
ALT
2006
Springer
8 years 10 months ago
Hannan Consistency in On-Line Learning in Case of Unbounded Losses Under Partial Monitoring
In this paper the sequential prediction problem with expert advice is considered when the loss is unbounded under partial monitoring scenarios. We deal with a wide class of the par...
Chamy Allenberg, Peter Auer, László ...
ALT
2008
Springer
9 years 3 months ago
Active Learning in Multi-armed Bandits
In this paper we consider the problem of actively learning the mean values of distributions associated with a finite number of options (arms). The algorithms can select which opti...
András Antos, Varun Grover, Csaba Szepesv&a...
ICML
2006
IEEE
9 years 7 months ago
Experience-efficient learning in associative bandit problems
We formalize the associative bandit problem framework introduced by Kaelbling as a learning-theory problem. The learning environment is modeled as a k-armed bandit where arm payof...
Alexander L. Strehl, Chris Mesterharm, Michael L. ...
books