An Asymptotically Optimal Strategy for Constrained Multi-armed Bandit Problems
Optimization and Control
2018-05-04 v1 Machine Learning
Machine Learning
Abstract
For the stochastic multi-armed bandit (MAB) problem from a constrained model that generalizes the classical one, we show that an asymptotic optimality is achievable by a simple strategy extended from the -greedy strategy. We provide a finite-time lower bound on the probability of correct selection of an optimal near-feasible arm that holds for all time steps. Under some conditions, the bound approaches one as time goes to infinity. A particular example sequence of having the asymptotic convergence rate in the order of that holds from a sufficiently large is also discussed.
Cite
@article{arxiv.1805.01237,
title = {An Asymptotically Optimal Strategy for Constrained Multi-armed Bandit Problems},
author = {Hyeong Soo Chang},
journal= {arXiv preprint arXiv:1805.01237},
year = {2018}
}