English

A Confirmation of a Conjecture on the Feldman's Two-armed Bandit Problem

Statistics Theory 2022-06-03 v1 Machine Learning Statistics Theory

Abstract

Myopic strategy is one of the most important strategies when studying bandit problems. In this paper, we consider the two-armed bandit problem proposed by Feldman. With general distributions and utility functions, we obtain a necessary and sufficient condition for the optimality of the myopic strategy. As an application, we could solve Nouiehed and Ross's conjecture for Bernoulli two-armed bandit problems that myopic strategy stochastically maximizes the number of wins.

Keywords

Cite

@article{arxiv.2206.00821,
  title  = {A Confirmation of a Conjecture on the Feldman's Two-armed Bandit Problem},
  author = {Zengjing Chen and Yiwei Lin and Jichen Zhang},
  journal= {arXiv preprint arXiv:2206.00821},
  year   = {2022}
}

Comments

19 pages, 0 figures