7 search results - page 1 / 2 » Pure Exploration in Multi-armed Bandits Problems |
NIPS
2008
13 years 6 months ago
2008
We formulate and study a new variant of the k-armed bandit problem, motivated by e-commerce applications. In our model, arms have (stochastic) lifetime after which they expire. In...
CORR
2010
Springer
13 years 4 months ago
2010
Springer
We consider the classical multi-armed bandit problem with Markovian rewards. When played an arm changes its state in a Markovian fashion while it remains frozen when not played. Th...
COLT
2010
Springer
13 years 2 months ago
2010
Springer
We consider the problem of finding the best arm in a stochastic multi-armed bandit game. The regret of a forecaster is here defined by the gap between the mean reward of the optim...
CORR
2010
Springer
13 years 4 months ago
2010
Springer
We consider the problem of revenue-optimal dynamic mechanism design in settings where agents' types evolve over time as a function of their (both public and private) experien...
SAC
2005
ACM
13 years 10 months ago
2005
ACM
Active learning is a generic approach to accelerate training of classifiers in order to achieve a higher accuracy with a small number of training examples. In the past, simple ac...