A Relative Exponential Weighing Algorithm for Adversarial Utility-based Dueling Bandits thumbnail
Pause
Mute
Subtitles not available
Playback speed
0.25
0.5
0.75
1
1.25
1.5
1.75
2
Full screen

A Relative Exponential Weighing Algorithm for Adversarial Utility-based Dueling Bandits

Published on Sep 27, 20152306 Views

We study the K-armed dueling bandit problem which is a variation of the classical Multi-Armed Bandit (MAB) problem in which the learner receives only relative feedback about the selected pairs of arms

Related categories