A note on maximal mean/standard deviation ratio in an undiscounted MDP

DOI10.1016/0167-6377(89)90061-8zbMath0679.90091OpenAlexW2004350543MaRDI QIDQ1823169

Kun-Jen Chung

Publication date: 1989

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

Full work available at URL: https://doi.org/10.1016/0167-6377(89)90061-8

zbMATH Keywords

mean-variancestationary policyundiscounted MDP

Mathematics Subject Classification ID

Discrete-time Markov processes on general state spaces (60J05) Applications of Markov chains and discrete-time Markov processes on general state spaces (social mobility, learning theory, industrial processes, etc.) (60J20) Markov and semi-Markov decision processes (90C40)

Related Items

A Fourth bibliography of fractional programming, Mean-variance criteria in an undiscounted Markov decision process, On mean-standard deviation ratio problems and beyond via c-programming, Notes on average Markov decision processes with a minimum-variance criterion

Cites Work

• Maximal mean/standard deviation ratio in an undiscounted MDP
• Mean, variance and probabilistic criteria in finite Markov decision processes: A review
• Mean-Variance Tradeoffs in an Undiscounted MDP
• On Linear Programming in a Markov Decision Problem