Optimal Exploration–Exploitation in a Multi-armed Bandit Problem with Non-stationary Rewards
Besbes, Omar, Gur, Yonatan, Zeevi, AssafLanguage:
english
Journal:
Stochastic Systems
DOI:
10.1287/stsy.2019.0033
Date:
October, 2019
File:
PDF, 1.51 MB
english, 2019