JMLR
2012
12 years 2 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...
AMAI
2011
Springer
13 years 14 days ago
2011
Springer
A multi-armed bandit episode consists of n trials, each allowing selection of one of K arms, resulting in payoff from a distribution over [0, 1] associated with that arm. We assum...
AGI
2011
13 years 4 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...
JMLR
2010
13 years 7 months ago
2010
This work deals with four classical prediction settings, namely full information, bandit, label efficient and bandit label efficient as well as four different notions of regret: p...
CORR
2008
Springer
14 years 17 days ago
2008
Springer
In a multi-armed bandit problem, an online algorithm chooses from a set of strategies in a sequence of n trials so as to maximize the total payoff of the chosen strategies. While ...
SDM
2007
SIAM
14 years 1 months ago
2007
SIAM
We consider a novel problem of learning an optimal matching, in an online fashion, between two feature spaces that are organized as taxonomies. We formulate this as a multi-armed ...