Corralling a Band of Bandit Algorithms

conference on learning theory, 2017.

Cited by: 43|Views84
EI

Abstract:

We study the problem of combining multiple bandit algorithms (that is, online learning algorithms with partial feedback) with the goal of creating a master algorithm that performs almost as well as the best base algorithm if it were to be run on its own. The main challenge is that when run with a master, base algorithms unavoidably receiv...More

Code:

Data:

Your rating :
0

 

Tags
Comments