Copeland Dueling Bandits.

Masrour Zoghi Zohar Shay Karnin Shimon Whiteson Maarten de Rijke

Published in: CoRR (2015)

Keyphrases

scoring rules
stochastic systems
multi armed bandits
regret bounds
multi armed bandit
data sets
multi agent systems
semi markov
computer vision
image segmentation
lower bound
least squares
stochastic models