Multi-objective infinite-horizon discounted Markov decision processes

DOI10.1016/0022-247X(82)90122-6zbMath0496.90083OpenAlexW2071279638MaRDI QIDQ1170120

Douglas J. White

Publication date: 1982

Published in: Journal of Mathematical Analysis and Applications (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1016/0022-247x(82)90122-6

zbMATH Keywords

efficient solutionsinfinite-horizon discounted Markov decision processesnonstationary policiesvector method of successive approximations

Mathematics Subject Classification ID

Sensitivity, stability, parametric optimization (90C31) Dynamic programming (90C39) Markov and semi-Markov decision processes (90C40)

Related Items (14)

Vector-valued Markov decision processes and the systems of linear inequalities ⋮ Compositional strategy synthesis for stochastic games with multiple objectives ⋮ A fuzzy approach to Markov decision processes with uncertain transition probabilities ⋮ A multi-objective approach for PH-graphs with applications to stochastic shortest paths ⋮ An extended ϵ‐constraint method for a multiobjective finite‐horizon Markov decision process ⋮ Markov decision processes ⋮ Optimal stationary policies in the vector-valued Markov decision process ⋮ Approximate saddle points for minmax problems and vector valued games. ⋮ Markov Decision Processes with Multiple Long-Run Average Objectives ⋮ Transfer in variable-reward hierarchical reinforcement learning ⋮ Linear programming in tector criterion markov and semi-Markov decision processes ⋮ Controlled Markov set-chains under average criteria ⋮ Epsilon efficiency ⋮ Multi-objective dynamic programming with limited precision

Cites Work

• Validity of Local Search in Multiparametric and Vector Linear Programming
• Note on Multiple Objective Dynamic Programming
• Kernels of Preference Structures
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item

This page was built for publication: Multi-objective infinite-horizon discounted Markov decision processes