Unbounded cost Markov decision processes with limsup and liminf average criteria: new conditions

DOI10.1007/s001860400408zbMath1114.90144OpenAlexW2052769973MaRDI QIDQ2573783

Yonglong Dai, Xianping Guo, Quanxin Zhu

Publication date: 24 November 2005

Published in: Mathematical Methods of Operations Research (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1007/s001860400408

zbMATH Keywords

optimal stationary policyunbounded costaverage criterionDiscrete-time Markov decision process

Mathematics Subject Classification ID

Dynamic programming (90C39) Markov and semi-Markov decision processes (90C40)

Related Items (8)

Markov Decision Processes with Variance Minimization: A New Condition and Approach ⋮ Bias optimality and strong \(n\) \((n= -1,0)\) discount optimality for Markov decision processes ⋮ A semimartingale characterization of average optimal stationary policies for Markov decision processes ⋮ Sample-path optimality and variance-maximization for Markov decision processes ⋮ Average optimality for continuous-time Markov decision processes with a policy iteration approach ⋮ Average optimality inequality for continuous-time Markov decision processes in Polish spaces ⋮ Another set of conditions for Markov decision processes with average sample-path costs ⋮ Constrained semi-Markov decision processes with ratio and time expected average criteria in Polish spaces

This page was built for publication: Unbounded cost Markov decision processes with limsup and liminf average criteria: new conditions