Mean-Variance Tradeoffs in an Undiscounted MDP

DOI10.1287/opre.42.1.175zbMath0798.90130OpenAlexW1980079915MaRDI QIDQ4287609

Matthew J. Sobel

Publication date: 12 April 1994

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

Full work available at URL: https://doi.org/10.1287/opre.42.1.175

zbMATH Keywords

Pareto optimastationary policypolicy improvementstationary probability distribution of the reward

Mathematics Subject Classification ID

Linear programming (90C05) Markov and semi-Markov decision processes (90C40)

Related Items (18)

Analyzing operational risk-reward trade-offs for start-ups ⋮ Minimum Average Value-at-Risk for Finite Horizon Semi-Markov Decision Processes in Continuous Time ⋮ Trading performance for stability in Markov decision processes ⋮ Markov Decision Problems Where Means Bound Variances ⋮ Risk-sensitive control of Markov decision processes: a moment-based approach with target distributions ⋮ Variance minimization for constrained discounted continuous-time MDPs with exponentially distributed stopping times ⋮ Optimization of Markov decision processes under the variance criterion ⋮ Mean-variance problems for finite horizon semi-Markov decision processes ⋮ A unified algorithm framework for mean-variance optimization in discounted Markov decision processes ⋮ Mean-variance optimization of discrete time discounted Markov decision processes ⋮ Almost Stochastic Dominance for Most Risk-Averse Decision Makers ⋮ Variance minimization of parameterized Markov decision processes ⋮ A note on maximal mean/standard deviation ratio in an undiscounted MDP ⋮ An Inequality for Variances of the Discounted Rewards ⋮ A Convex Analytic Approach to Risk-Aware Markov Decision Processes ⋮ Mean-variance criteria in an undiscounted Markov decision process ⋮ Maximal mean/standard deviation ratio in an undiscounted MDP ⋮ Notes on average Markov decision processes with a minimum-variance criterion

This page was built for publication: Mean-Variance Tradeoffs in an Undiscounted MDP