Login / Signup
Approximate Indexability and Bandit Problems with Concave Rewards and Delayed Feedback.
Sudipto Guha
Kamesh Munagala
Published in:
APPROX-RANDOM (2013)
Keyphrases
</>
bandit problems
delayed feedback
multi armed bandits
decision problems
piecewise linear
exploration exploitation
objective function
decentralized decision making
learning algorithm
lower bound
genetic algorithm