Asymptotically optimal algorithms for budgeted multiple play bandits

DOI10.1007/s10994-019-05799-xzbMath1446.91032arXiv1606.09388OpenAlexW2964045314MaRDI QIDQ2331676

Emilie Kaufmann, Antoine Chambaz, Alex Luedtke

Publication date: 30 October 2019

Published in: Machine Learning (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1606.09388

zbMATH Keywords

Thompson samplingbudgeted banditsKl-UCBknapsack banditsmultiple-play bandits

Mathematics Subject Classification ID

Probabilistic games; gambling (91A60) Algorithmic game theory and complexity (91A68)

Related Items

Adaptive policies for perimeter surveillance problems ⋮ Asymptotically optimal algorithms for budgeted multiple play bandits

Uses Software

• R

Cites Work

• Unnamed Item
• Kullback-Leibler upper confidence bounds for optimal sequential allocation
• Combinatorial bandits
• Asymptotically efficient adaptive allocation rules
• Adaptive treatment allocation and the multi-armed bandit problem
• Optimal adaptive policies for sequential allocation problems
• Asymptotically optimal algorithms for budgeted multiple play bandits
• Thompson Sampling: An Asymptotically Optimal Finite-Time Analysis
• Asymptotically efficient allocation rules for the multiarmed bandit problem with multiple plays-Part I: I.I.D. rewards
• Bandits with Knapsacks
• Near-Optimal Regret Bounds for Thompson Sampling
• Explore First, Exploit Next: The True Shape of Regret in Bandit Problems
• Discrete-Variable Extremum Problems
• Some aspects of the sequential design of experiments

This page was built for publication: Asymptotically optimal algorithms for budgeted multiple play bandits