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"

6 / 6 papers shown

Title
On the Convergence of Monte Carlo UCB for Random-Length Episodic MDPs Zixuan Dong Che Wang Keith Ross 33 3 0 07 Sep 2022
Algorithms for Differentially Private Multi-Armed Bandits Aristide C. Y. Tossou Christos Dimitrakakis FedML 22 110 0 27 Nov 2015
Asymptotically Optimal Sequential Experimentation Under Generalized Ranking Wesley Cowan M. Katehakis OffRL 30 11 0 07 Oct 2015
Asymptotically Optimal Multi-Armed Bandit Policies under a Cost Constraint A. Burnetas Odysseas Kanavetas M. Katehakis 17 15 0 09 Sep 2015
An Asymptotically Optimal Policy for Uniform Bandits of Unknown Support Wesley Cowan M. Katehakis 29 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 32 22 0 22 Apr 2015