A mathematical programming approach to a problem in variance penalised Markov decision processes

DOI10.1007/BF01719453zbMath0793.90092MaRDI QIDQ1317531

Douglas J. White

Publication date: 17 March 1994

Published in: OR Spektrum (Search for Journal in Brave)

zbMATH Keywords

varianceaverage expected reward\(\varepsilon\)-optimal solution

Mathematics Subject Classification ID

Markov and semi-Markov decision processes (90C40)

Related Items (1)

Finite-horizon variance penalised Markov decision processes

Cites Work

• Unnamed Item
• A variance minimization problem for a Markov decision process
• Computational approaches to variance-penalised Markov decision processes
• VARIANCE CONSTRAINED MARKOV DECISION PROCESS
• Variance-Penalized Markov Decision Processes
• A Successive Underestimation Method for Concave Minimization Problems
• Solving Certain Nonconvex Quadratic Minimization Problems by Ranking the Extreme Points
• Solving the Fixed Charge Problem by Ranking the Extreme Points

This page was built for publication: A mathematical programming approach to a problem in variance penalised Markov decision processes