44 search results - page 4 / 9 » A structured multiarmed bandit problem and the greedy policy |
CORR
2010
Springer
13 years 7 months ago
2010
Springer
We consider the restless multi-armed bandit (RMAB) problem with unknown dynamics. In this problem, at each time, a player chooses K out of N (N > K) arms to play. The state of ...
CORR
2010
Springer
13 years 2 months ago
2010
Springer
In the classic multi-armed bandits problem, the goal is to have a policy for dynamically operating arms that each yield stochastic rewards with unknown means. The key metric of int...
ICASSP
2011
IEEE
12 years 11 months ago
2011
IEEE
Abstract—We consider the restless multi-armed bandit (RMAB) problem with unknown dynamics. At each time, a player chooses K out of N (N > K) arms to play. The state of each ar...
COLT
2010
Springer
13 years 5 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...
JMLR
2012
11 years 9 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...