A better resource allocation algorithm with semi-bandit feedback

MaRDI QIDQ4617606zbMATH OpenFDO

Authors Yuval Dagan, Koby Crammer

Publication date 6 February 2019

Full work available at URL https://arxiv.org/abs/1803.10415, http://proceedings.mlr.press/v83/dagan18a/dagan18a.pdf

Mathematics Subject Classification ID

Sequential statistical analysis (62L10) Resource and cost allocation (including fair division, apportionment, etc.) (91B32) Compound decision problems in statistical decision theory (62C25) Optimal stopping in statistics (62L15) Probabilistic games; gambling (91A60)

Recommendations

• On Bayesian index policies for sequential resource allocation
• An Efficient Algorithm for Learning with Semi-bandit Feedback
• Asymptotically efficient allocation rules for the multiarmed bandit problem with multiple plays-Part I: I.I.D. rewards
• Kullback-Leibler upper confidence bounds for optimal sequential allocation
• On the improvement of allocation rules for multi-armed bandit problem

Cited in

(3)

• Importance weighting without importance weights: an efficient algorithm for combinatorial semi-bandits
• Multi-armed bandits with censored consumption of resources
• An Efficient Algorithm for Learning with Semi-bandit Feedback

This page was built for publication: A better resource allocation algorithm with semi-bandit feedback

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4617606)