video thumbnail
Pause
Mute
Subtitles
Playback speed
0.25
0.5
0.75
1
1.25
1.5
1.75
2
Full screen

Bounded regret in stochastic multi-armed bandits

Published on 2013-08-095569 Views

We study the stochastic multi-armed bandit problem when one knows the value μ(⋆) of an optimal arm, as a well as a positive lower bound on the smallest positive gap Δ. We propose a new randomized poli

Related categories

Presentation

Bounded regret in stochastic multi-armed bandits - 100:00
Bounded regret in stochastic multi-armed bandits - 200:10
Bounded regret in stochastic multi-armed bandits - 300:21