66 search results - page 4 / 14 » The Nonstochastic Multiarmed Bandit Problem |
CORR
2006
Springer
13 years 7 months ago
2006
Springer
While in general trading off exploration and exploitation in reinforcement learning is hard, under some formulations relatively simple solutions exist. Optimal decision thresholds ...
CDC
2008
IEEE
14 years 2 months ago
2008
IEEE
—We consider a multiarmed bandit problem where the expected reward of each arm is a linear function of an unknown scalar with a prior distribution. The objective is to choose a s...
CORR
2010
Springer
13 years 7 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...
ALT
2009
Springer
14 years 4 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...
CORR
2010
Springer
13 years 2 months ago
2010
Springer
We consider a combinatorial generalization of the classical multi-armed bandit problem that is defined as follows. There is a given bipartite graph of M users and N M resources. F...