Bandit problems with arbitrary side observations.

Chih-Chun Wang Sanjeev R. Kulkami H. Vincent Poor

Published in: CDC (2003)

Keyphrases

bandit problems
multi armed bandits
decision problems
exploration exploitation
multi agent systems
decentralized decision making
multi armed bandit problems
artificial intelligence
decision making
multi agent
search space
evolutionary algorithm
hidden markov models
upper bound
graphical models
user defined