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 Sep 06, 20122413 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
Chapter list
From Bandits to Experts: On the Value of Side-Observations00:00
What We Do00:09
Why01:15
Results02:34