Login / Signup
Combinatorial Network Optimization With Unknown Variables: Multi-Armed Bandits With Linear Rewards and Individual Observations.
Yi Gai
Bhaskar Krishnamachari
Rahul Jain
Published in:
IEEE/ACM Trans. Netw. (2012)
Keyphrases
</>
multi armed bandits
bandit problems
highly non linear
network structure
optimization problems
optimization algorithm
closed form
noisy observations
learning algorithm
reinforcement learning