"A learning algorithm for the finite-time two-armed bandit problem."

Mitsuo Sato, Kenichi Abe, Hiroshi Takeda (1984)

Details and statistics

DOI: 10.1109/TSMC.1984.6313253

access: closed

type: Journal Article

metadata version: 2020-05-20

a service of  Schloss Dagstuhl - Leibniz Center for Informatics