Information collection on a graph

DOI10.1287/OPRE.1100.0873MaRDI QIDQ3013928zbMATH OpenOpenAlexFDO

Authors Ilya O. Ryzhov, Warren Powell

Publication date 19 July 2011

Published in Operations Research (Search for Journal in Brave)

Full work available at URL https://semanticscholar.org/paper/0c550c0b722139663f9c184074515b0506227182

zbMATH Keywords

Bayesian learningknowledge gradientoptimal learningranking and selectionstochastic shortest paths

Mathematics Subject Classification ID

Programming involving graphs or networks (90C35)

Recommendations

• A Knowledge-Gradient Policy for Sequential Information Collection
• Refined knowledge-gradient policy for learning probabilities
• The knowledge gradient algorithm for a general class of online learning problems
• The knowledge-gradient policy for correlated normal beliefs
• Finite-time analysis for the knowledge-gradient policy

Cited in

(7)

• On the convergence rates of expected improvement methods
• The post-disaster debris clearance problem under incomplete information
• Optimal information blending with measurements in the \(L^{2}\) sphere
• Nonstationary bandits with habituation and recovery dynamics
• Learning in combinatorial optimization: what and how to explore
• Risk-averse approximate dynamic programming with quantile-based risk measures
• Optimal sequential stochastic shortest path interdiction

This page was built for publication: Information collection on a graph

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q3013928)