Learning to Play K-armed Bandit Problems.

Francis Maes Louis Wehenkel Damien Ernst

Published in: ICAART (1) (2012)

Keyphrases

learning algorithm
learning systems
online learning
lower bound
learning process
unsupervised learning
domain independent
inductive inference
genetic algorithm
feature selection
decision trees
reinforcement learning
empirical studies
background knowledge
incremental learning
learning community