117
click to vote
JMLR
2012
13 years 19 days 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...
140
click to vote
AMAI
2011
Springer
13 years 10 months 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...
107
click to vote
AGI
2011
14 years 1 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...
87
Voted
JMLR
2010
14 years 5 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...
90
Voted
CORR
2008
Springer
14 years 10 months 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 ...
86
Voted
SDM
2007
SIAM
14 years 11 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 ...