Technical Note—On the Convexity of Policy Regions in Partially Observed Systems

DOI10.1287/OPRE.35.4.619zbMATH Open0635.90099OpenAlexW1986287620MaRDI QIDQ3775355FDOQ3775355

Authors: William S. Lovejoy 

Publication date: 1987

Published in: Operations Research (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1287/opre.35.4.619

Recommendations

• scientific article; zbMATH DE number 703928
• A Lyapunov characterization of robust policy optimization
• scientific article; zbMATH DE number 7626790
• Using Convex Switching Techniques for Partially Observable Decision Processes
• Regret bounds and minimax policies under partial monitoring
• 10.1162/153244303768966102
• Partially observable stochastic optimal control
• Accuracy of policy function approximations for strongly concave recursive problems
• Convex Optimization for Parameter Synthesis in MDPs
• scientific article; zbMATH DE number 970077

zbMATH Keywords

partially observed systemsconvex policy region results

Mathematics Subject Classification ID

Markov and semi-Markov decision processes (90C40)

Cited In (8)

• Ambiguous partially observable Markov decision processes: structural results and applications
• A model of project evaluation with limited attention
• Patient-type Bayes-adaptive treatment plans
• Multistate Bayesian control chart over a finite horizon
• Using Convex Switching Techniques for Partially Observable Decision Processes
• On the average cost optimality equation and the structure of optimal policies for partially observable Markov decision processes
• Optimal Threshold Policies for Multivariate Stopping-Time POMDPs
• A linear-quadratic Gaussian approach to dynamic information acquisition

This page was built for publication: Technical Note—On the Convexity of Policy Regions in Partially Observed Systems

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q3775355)