Learning in a Changing World: Restless Multiarmed Bandit With Unknown Dynamics.

Haoyang Liu Keqin Liu Qing Zhao

Published in: IEEE Trans. Inf. Theory (2013)

Keyphrases

learning process
incremental learning
learning algorithm
learning tasks
active learning
supervised learning
online learning
unsupervised learning
learning systems
computer programming
prior knowledge
optimal control
recurrent networks
multiarmed bandit