Multi-objective multi-armed bandit with lexicographically ordered and satisficing objectives

DOI10.1007/S10994-021-05956-1MaRDI QIDQ2051318zbMATH OpenOpenAlexFDO

Authors Alihan Hüyük, Cem Tekin

Publication date 24 November 2021

Published in Machine Learning (Search for Journal in Brave)

Full work available at URL http://hdl.handle.net/11693/77165

zbMATH Keywords

lexicographic optimalitymulti-armed banditmulti-objective learningsatisficing

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05)

Recommendations

• Satisficing in Time-Sensitive Bandit Learning
• Constrained regret minimization for multi-criterion multi-armed bandits
• Model-Free Reinforcement Learning for Lexicographic Omega-Regular Objectives
• Interactive Thompson sampling for multi-objective multi-armed bandits

Cites work

• A Structured Multiarmed Bandit Problem and the Greedy Policy
• Active learning in heteroscedastic noise
• Asymptotically efficient adaptive allocation rules
• Bandit algorithms
• Contextual bandits with similarity information
• Exceptional Paper—Lexicographic Orders, Utilities and Decision Rules: A Survey
• Explore first, exploit next: the true shape of regret in bandit problems
• scientific article; zbMATH DE number 6202411 (Why is no real title available?)
• Multi-objective Contextual Multi-armed Bandit With a Dominant Objective
• Multicriteria Optimization
• Optimal sequential sampling from two populations.
• Satisficing in Multi-Armed Bandit Problems

Cited in

(3)

• scientific article; zbMATH DE number 7626733 (Why is no real title available?)
• Satisficing in Time-Sensitive Bandit Learning
• Lexicographic Lipschitz bandits: new algorithms and a lower bound

This page was built for publication: Multi-objective multi-armed bandit with lexicographically ordered and satisficing objectives

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2051318)