A successive approximation algorithm for an undiscounted Markov decision process

DOI10.1007/BF02276760zbMath0339.60069OpenAlexW2163408601MaRDI QIDQ1231344

K. Appert

Publication date: 1976

Published in: Computing (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1007/bf02276760

Mathematics Subject Classification ID

Optimal stochastic control (93E20) Applications of Markov chains and discrete-time Markov processes on general state spaces (social mobility, learning theory, industrial processes, etc.) (60J20)

Related Items (3)

Some basic concepts of numerical treatment of Markov decision models ⋮ The method of value oriented successive approximations for the average reward Markov decision process ⋮ Improved iterative computation of the expected discounted return in Markov and semi-Markov chains

Cites Work

• Unnamed Item
• Bewertete Markovprozesse im stationären Zustand - Ein neuer Algorithmus mit Beispiel
• A set of successive approximation methods for discounted Markovian decision problems
• On Finding the Maximal Gain for Markov Decision Processes

This page was built for publication: A successive approximation algorithm for an undiscounted Markov decision process