A near-optimal algorithm for finite partial-monitoring games against adversarial opponents thumbnail
Pause
Mute
Subtitles
Playback speed
0.25
0.5
0.75
1
1.25
1.5
1.75
2
Full screen

A near-optimal algorithm for finite partial-monitoring games against adversarial opponents

Published on Aug 09, 20132941 Views

Partial monitoring is an online learning model where in every time step, after a learner and an opponent choose their actions, the loss and the feedback for the learner is calculated based on a loss a

Related categories

Chapter list

A near-optimal algorithm for finite partial-monitoring games against adversarial opponents00:00
Partial-Monitoring Games00:20
Measure of Performance of the Learner00:46
Recent previous work01:00
New algorithm GlogalExp302:48
New algorithm II: Choosing the local game - 103:27
New algorithm II: Choosing the local game - 204:10
New algorithm II: Choosing the local game - 304:11
New algorithm II: Choosing the local game - 404:30
New algorithm III: Playing the local game04:45
Main theorem05:14