scientific article; zbMATH DE number 977756

MaRDI QIDQ4331900zbMATHFDO

Authors Arie Hordijk, Eitan Altman, Lodewijk Kallenberg

Publication date 13 February 1997

zbMATH Keywords

value functionLaurent series expansionfinitely many states and actionsunconstrained Markov decision process

Mathematics Subject Classification ID

Markov and semi-Markov decision processes (90C40)

Recommendations

• Towards the optimal control of Markov chains with constraints
• Continuity of Optimal Values and Solutions for Control of Markov Chains with Constraints
• Convergence of the optimal values of constrained Markov control processes
• Optimal policies for controlled Markov chains with a constraint
• Control of a Markov process in a problem with constraints
• scientific article; zbMATH DE number 3950345
• scientific article; zbMATH DE number 4203409

Cited in

(3)

• A note on the convergence rate of the value iteration scheme in controlled Markov chains
• Continuity of Optimal Values and Solutions for Control of Markov Chains with Constraints
• The value functions of Markov decision processes

This page was built for publication:

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4331900)