A variance minimization problem for a Markov decision process

DOI10.1016/0377-2217(87)90148-2zbMath0623.90087OpenAlexW1972505433MaRDI QIDQ1091952

Hajime Kawai

Publication date: 1987

Published in: European Journal of Operational Research (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1016/0377-2217(87)90148-2

zbMATH Keywords

finite statesdiscrete time Markov decision processfinite actionsoptimal random policyparametric Markov decision processvariance of reward

Mathematics Subject Classification ID

Markov and semi-Markov decision processes (90C40)

Related Items

Analyzing operational risk-reward trade-offs for start-ups ⋮ Markov Decision Problems Where Means Bound Variances ⋮ Multi-objective discounted Markov decision processes with expectation and variance criteria ⋮ Survey of linear programming for standard and nonstandard Markovian control problems. Part I: Theory ⋮ Time-inconsistent risk-sensitive equilibrium for countable-stated Markov decision processes ⋮ On the total reward variance for continuous-time Markov reward chains ⋮ Mean-Variance Analysis in Infinite Horizon Non-Discounted Markov Decision Processes: Technical Note ⋮ Mean-variance criteria in an undiscounted Markov decision process ⋮ A mathematical programming approach to a problem in variance penalised Markov decision processes ⋮ On mean reward variance in semi-Markov processes ⋮ Algorithmic aspects of mean-variance optimization in Markov decision processes ⋮ Notes on average Markov decision processes with a minimum-variance criterion

Cites Work

• Unnamed Item
• Unnamed Item
• Optimal policies for controlled Markov chains with a constraint
• Markov decision processes with a new optimality criterion: Discrete time
• Finite state Markovian decision processes
• Calculating the variance in Markov-processes with random reward
• Constrained Undiscounted Stochastic Dynamic Programming
• The variance of discounted Markov decision processes