16 search results - page 1 / 4 » Deviations of Stochastic Bandit Regret |
ALT
2011
Springer
12 years 4 months ago
2011
Springer
This paper studies the deviations of the regret in a stochastic multi-armed bandit problem. When the total number of plays n is known beforehand by the agent, Audibert et al. (2009...
ALT
2009
Springer
14 years 1 months ago
2009
Springer
Abstract. We consider the framework of stochastic multi-armed bandit problems and study the possibilities and limitations of strategies that explore sequentially the arms. The stra...
ALT
2007
Springer
14 years 1 months ago
2007
Springer
Algorithms based on upper-confidence bounds for balancing exploration and exploitation are gaining popularity since they are easy to implement, efficient and effective. In this p...
CORR
2012
Springer
12 years 1 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...
JMLR
2010
12 years 11 months ago
2010
This work deals with four classical prediction settings, namely full information, bandit, label efficient and bandit label efficient as well as four different notions of regret: p...