en
0.25
0.5
0.75
1.25
1.5
1.75
2
From Bandits to Experts: On the Value of Side-Observations
Published on 2012-09-062419 Views
We consider an adversarial online learning setting where a decision maker can choose an action in every stage of the game. In addition to observing the reward of the chosen action, the decision maker
Related categories
Presentation
From Bandits to Experts: On the Value of Side-Observations00:00
What We Do00:09
Why01:15
Results02:34