70 citations · 245 across the 36 of their papers we have counts for
Showing math.STShow all
3 papers · 1 filter
math.ST2013★ 44 cited
Optimality of Thompson Sampling for Gaussian Bandits Depends on Priors
Junya Honda, Akimichi Takemura
In stochastic bandit problems, a Bayesian policy called Thompson sampling (TS) has recently attracted much attention for its excellent empirical performance. However, the theoretic…
math.ST2012★ 3 cited
Finite-time Regret Bound of a Bandit Algorithm for the Semi-bounded Support Model
Junya Honda, Akimichi Takemura
In this paper we consider stochastic multiarmed bandit problems. Recently a policy, DMED, is proposed and proved to achieve the asymptotic bound for the model that each reward dist…
math.ST2009★ 2 cited
An Asymptotically Optimal Policy for Finite Support Models in the Multiarmed Bandit Problem
Junya Honda, Akimichi Takemura
We propose minimum empirical divergence (MED) policy for the multiarmed bandit problem. We prove asymptotic optimality of the proposed policy for the case of finite support models.…