44 search results - page 2 / 9 » A structured multiarmed bandit problem and the greedy policy |
CDC
2009
IEEE
14 years 2 days ago
2009
IEEE
We consider a class of restless multi-armed bandit problems that arises in multi-channel opportunistic communications, where channels are modeled as independent and stochastically...
TSP
2010
13 years 2 months ago
2010
We formulate and study a decentralized multi-armed bandit (MAB) problem. There are distributed players competing for independent arms. Each arm, when played, offers i.i.d. reward a...
ICASSP
2010
IEEE
13 years 7 months ago
2010
IEEE
—We consider a cognitive radio network with distributed multiple secondary users, where each user independently searches for spectrum opportunities in multiple channels without e...
AGI
2011
12 years 11 months ago
2011
We present an actor-critic scheme for reinforcement learning in complex domains. The main contribution is to show that planning and I/O dynamics can be separated such that an intra...
COLT
2003
Springer
14 years 17 days ago
2003
Springer
We consider the Multi-armed bandit problem under the PAC (“probably approximately correct”) model. It was shown by Even-Dar et al. [5] that given n arms, it suffices to play th...