Online Non-Additive Path Learning under Full and Partial Information

algorithmic learning theory, 2019.

Cited by: 0|Views54
EI

Abstract:

We consider the online path learning problem in a graph with non-additive gains/losses. Various settings of full information, semi-bandit, and full bandit are explored. We give an efficient implementation of EXP3 algorithm for the full bandit setting with any (non-additive) gain. Then, focusing on the large family of non-additive count-ba...More

Code:

Data:

Your rating :
0

 

Tags
Comments