Asymptotic Behavior of Minimal-Exploration Allocation Policies: Almost Sure, Arbitrarily Slow Growing Regret

12 May 2015

Papers citing "Asymptotic Behavior of Minimal-Exploration Allocation Policies: Almost Sure, Arbitrarily Slow Growing Regret"

5 / 5 papers shown

Title
On the Convergence of Monte Carlo UCB for Random-Length Episodic MDPs Zixuan Dong Che Wang George Andriopoulos 45 3 0 07 Sep 2022
An Asymptotically Optimal Policy for Uniform Bandits of Unknown Support Wesley Cowan M. Katehakis 110 27 0 08 May 2015
Normal Bandits of Unknown Means and Variances: Asymptotic Optimality, Finite Horizon Regret Bounds, and a Solution to an Open Problem Wesley Cowan Junya Honda M. Katehakis 89 22 0 22 Apr 2015
Optimality of Thompson Sampling for Gaussian Bandits Depends on Priors Junya Honda Akimichi Takemura 44 63 0 08 Nov 2013
An Asymptotically Optimal Policy for Finite Support Models in the Multiarmed Bandit Problem Junya Honda Akimichi Takemura 99 121 0 17 May 2009