Budgeted multi-armed bandit in continuous action space

DOI10.3233/978-1-61499-672-9-560MaRDI QIDQ4576192zbMATH OpenOpenAlexFDO

Authors Francesco Trovò, Stefano Paladino, Marcello Restelli, Nicola Gatti

Publication date 12 July 2018

Full work available at URL https://doi.org/10.3233/978-1-61499-672-9-560

zbMATH Keywords

continuous action spacebudgeted multi-armed bandit

Mathematics Subject Classification ID

Software, source code, etc. for problems pertaining to game theory, economics, and finance (91-04) Probabilistic games; gambling (91A60)

Recommendations

• Approximation algorithms for budgeted learning problems
• Asymptotically optimal algorithms for budgeted multiple play bandits
• The Continuum-Armed Bandit Problem
• Differentially private and budget-limited bandit learning over matroids
• Learning Theory

Cited in

(5)

• Efficient, optimal stochastic-action selection when limited by an action budget
• Online joint bid/daily budget optimization of Internet advertising campaigns
• Learning Theory
• Asymptotically optimal algorithms for budgeted multiple play bandits
• Differentially private and budget-limited bandit learning over matroids

This page was built for publication: Budgeted multi-armed bandit in continuous action space

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4576192)