Contextual Bandits with Continuous Actions: Smoothing, Zooming, and Adapting

conference on learning theory, pp. 2025-2027, 2019.

Cited by: 19|Bibtex|Views80
EI
Other Links: dblp.uni-trier.de|academic.microsoft.com|arxiv.org

Abstract:

We study contextual bandit learning with an abstract policy class and continuous action space. We obtain two qualitatively different regret bounds: one competes with a smoothed version of the policy class under no continuity assumptions, while the other requires standard Lipschitz assumptions. Both bounds exhibit data-dependent "zooming...More

Code:

Data:

Full Text
Your rating :
0

 

Tags
Comments