An Inequality for Variances of the Discounted Rewards

DOI10.1239/jap/1261670699zbMath1187.60030OpenAlexW2030712766MaRDI QIDQ3402070

Eugene A. Feinberg, Jun Fei

Publication date: 2 February 2010

Published in: Journal of Applied Probability (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1239/jap/1261670699

zbMATH Keywords

stopping timevariancetotal discounted reward

Mathematics Subject Classification ID

Stopping times; optimal stopping problems; gambling theory (60G40) Markov and semi-Markov decision processes (90C40)

Related Items (5)

Markov Decision Problems Where Means Bound Variances ⋮ Variance minimization for constrained discounted continuous-time MDPs with exponentially distributed stopping times ⋮ A probability criterion for zero-sum stochastic games ⋮ Stochastic Comparison of Discounted Rewards ⋮ Absorbing Continuous-Time Markov Decision Processes with Total Cost Criteria

Cites Work

• Unnamed Item
• Unnamed Item
• Maximal mean/standard deviation ratio in an undiscounted MDP
• Markov decision processes with a new optimality criterion: Continuous time
• Mean, variance and probabilistic criteria in finite Markov decision processes: A review
• Mean-Variance Tradeoffs in an Undiscounted MDP
• The variance of discounted Markov decision processes
• SEMI-MARKOV DECISION PROCESSES
• On the total reward variance for continuous-time Markov reward chains
• Continuous Time Discounted Jump Markov Decision Processes: A Discrete-Event Approach

This page was built for publication: An Inequality for Variances of the Discounted Rewards