An index-based deterministic convergent optimal algorithm for constrained multi-armed bandit problems

DOI10.1016/J.AUTOMATICA.2021.109673OpenAlexW3159888357MaRDI QIDQ2665165

Hyeong Soo Chang

Publication date: 18 November 2021

Published in: Automatica (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2007.14550

zbMATH Keywords

learning theorymulti-armed banditconstrained simulation-optimization

Mathematics Subject Classification ID

Artificial intelligence (68Txx) Calculus of variations and optimal control; optimization (49-XX)

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• An asymptotically optimal strategy for constrained multi-armed bandit problems
• Sample average approximation of expected value constrained stochastic programs
• Asymptotically efficient adaptive allocation rules
• The Sample Average Approximation Method for Stochastic Discrete Optimization
• Randomised allocation of treatments in sequential trials
• Simple Bayesian Algorithms for Best-Arm Identification
• Stochastically Constrained Ranking and Selection via SCORE
• Probability Inequalities for Sums of Bounded Random Variables
• Prediction, Learning, and Games
• Some aspects of the sequential design of experiments
• Finite-time analysis of the multiarmed bandit problem

This page was built for publication: An index-based deterministic convergent optimal algorithm for constrained multi-armed bandit problems