Stochastic Linear Bandits Robust to Adversarial Attacks

Cited by: 1|Bibtex|Views35
Other Links: arxiv.org

Abstract:

We consider a stochastic linear bandit problem in which the rewards are not only subject to random noise, but also adversarial attacks subject to a suitable budget $C$ (i.e., an upper bound on the sum of corruption magnitudes across the time horizon). We provide two variants of a Robust Phased Elimination algorithm, one that knows $C$ a...More

Code:

Data:

Full Text
Your rating :
0

 

Tags
Comments