Combinatorial Network Optimization with Unknown Variables: Multi-Armed Bandits with Linear Rewards

Yi Gai Bhaskar Krishnamachari Rahul Jain

Published in: CoRR (2010)

Keyphrases

multi armed bandits
bandit problems
optimization algorithm
network structure
highly non linear
optimization problems
random variables
bayesian networks
reinforcement learning
evolutionary algorithm
decision problems
multi armed bandit
machine learning
markov decision processes
missing values