66 search results - page 1 / 14 » The Nonstochastic Multiarmed Bandit Problem |
COLT
2008
Springer
13 years 6 months ago
2008
Springer
We introduce an efficient algorithm for the problem of online linear optimization in the bandit setting which achieves the optimal O ( T) regret. The setting is a natural general...
SIAMCOMP
2002
13 years 4 months ago
2002
Abstract. In the multiarmed bandit problem, a gambler must decide which arm of K nonidentical slot machines to play in a sequence of trials so as to maximize his reward. This class...
JMLR
2012
11 years 7 months ago
2012
We develop a new tool for data-dependent analysis of the exploration-exploitation trade-off in learning under limited feedback. Our tool is based on two main ingredients. The fi...
CORR
2012
Springer
12 years 17 days ago
2012
Springer
We present a bandit algorithm, SAO (Stochastic and Adversarial Optimal), whose regret is, essentially, optimal both for adversarial rewards and for stochastic rewards. Specifical...
ECML
2005
Springer
13 years 10 months ago
2005
Springer
The multi-armed bandit problem for a gambler is to decide which arm of a K-slot machine to pull to maximize his total reward in a series of trials. Many real-world learning and opt...