74 search results - page 5 / 15 » Regret Bounds for Gaussian Process Bandit Problems |
117
click to vote
ICML
2009
IEEE
16 years 2 months ago
2009
IEEE
We consider a sequential decision problem where the rewards are generated by a piecewise-stationary distribution. However, the different reward distributions are unknown and may c...
132
click to vote
CORR
2010
Springer
15 years 1 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 ...
132
click to vote
COLT
2010
Springer
14 years 11 months ago
2010
Springer
We consider a bandit problem which involves sequential sampling from two populations (arms). Each arm produces a noisy reward realization which depends on an observable random cov...
121
click to vote
COLT
2005
Springer
15 years 3 months ago
2005
Springer
External regret compares the performance of an online algorithm, selecting among N actions, to the performance of the best of those actions in hindsight. Internal regret compares ...
151
click to vote
JMLR
2012
13 years 4 months ago
2012
Contextual bandit learning is a reinforcement learning problem where the learner repeatedly receives a set of features (context), takes an action and receives a reward based on th...