First-order regret bounds for combinatorial semi-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

First-order regret bounds for combinatorial semi-bandits

Published on Aug 20, 20151705 Views

We consider the problem of online combinatorial optimization under semi-bandit feedback, where a learner has to repeatedly pick actions from a combinatorial decision set in order to minimize the total

Related categories

Chapter list

First-order regret bounds for combinatorial semi-bandits00:00
Combinatorial semi-bandits - 100:10
Combinatorial semi-bandits - 200:21
Combinatorial semi-bandits - 300:47
Regret - 100:55
Regret - 201:20
First-order bounds - 101:24
First-order bounds - 202:19
This paper02:43
Thanks!04:04