Technical Note—Bounds on the Gain of a Markov Decision Process

DOI10.1287/opre.19.1.240zbMath0216.54804OpenAlexW2092187522MaRDI QIDQ5620496

N. A. J. Hastings

Publication date: 1971

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

Full work available at URL: https://doi.org/10.1287/opre.19.1.240

Mathematics Subject Classification ID

Markov and semi-Markov decision processes (90C40) Applications of Markov renewal processes (reliability, queueing networks, etc.) (60K20)

Related Items

Variational characterizations in Markov decision processes ⋮ Unnamed Item ⋮ Some basic concepts of numerical treatment of Markov decision models ⋮ The method of value oriented successive approximations for the average reward Markov decision process ⋮ An iterative method for approximating average cost optimal (s,S) inventory policies ⋮ Contraction mappings underlying undiscounted Markov decision problems ⋮ Generalized polynomial approximations in Markovian decision processes ⋮ Zur Extrapolation in Markoffschen Entscheidungsmodellen mit Diskontierung