图 书 馆开课单位--COLT 2011-布达佩斯
1 1/1
1The KL-UCB Algorithm for Bounded Stochastic Bandits and Beyond[KL-UCB算法用于有界随机带及其以外]
Aurélien Garivier(COLT 2011-布达佩斯) This paper presents a finite-time analysis of the KL-UCB algorithm, an online, horizon-free index policy for stochastic bandit problems. We prove two ...
热度：4
Aurélien Garivier(COLT 2011-布达佩斯) This paper presents a finite-time analysis of the KL-UCB algorithm, an online, horizon-free index policy for stochastic bandit problems. We prove two ...
热度：4
1 1/1