2 search results - page 1 / 1 » The value of information in multi-armed bandits with exponen... |
PROCEDIA
2011
12 years 7 months ago
2011
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...