English

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 ϵt\epsilon_t-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 tt goes to infinity. A particular example sequence of {ϵt}\{\epsilon_t\} having the asymptotic convergence rate in the order of (11t)4(1-\frac{1}{t})^4 that holds from a sufficiently large tt is also discussed.

Keywords

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}
}
R2 v1 2026-06-23T01:43:53.806Z