An asymptotically optimal strategy for constrained multi-armed bandit problems

DOI10.1007/S00186-019-00697-3zbMath1447.90022arXiv1805.01237OpenAlexW2997070617WikidataQ126414170 ScholiaQ126414170MaRDI QIDQ784789

Hyeong Soo Chang

Publication date: 3 August 2020

Published in: Mathematical Methods of Operations Research (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1805.01237

zbMATH Keywords

multi-armed banditconstrained stochastic optimizationsimulation optimizationconstrained Markov decision process

Mathematics Subject Classification ID

Stochastic programming (90C15) Markov and semi-Markov decision processes (90C40)

Related Items (1)

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

Cites Work

• Unnamed Item
• The multi-armed bandit, with constraints
• Sample average approximation of expected value constrained stochastic programs
• Asymptotically efficient adaptive allocation rules
• Algorithms for stochastic optimization with function or expectation constraints
• Pure exploration in finitely-armed and continuous-armed bandits
• Penalty Function with Memory for Discrete Optimization via Simulation with Stochastic Constraints
• Online Learning Methods for Networking
• Multi‐Armed Bandit Allocation Indices
• Randomised allocation of treatments in sequential trials
• Introduction to Stochastic Search and Optimization
• 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 asymptotically optimal strategy for constrained multi-armed bandit problems