Another set of verifiable conditions for average Markov decision processes with Borel spaces.

DOI10.14736/KYB-2015-2-0276MaRDI QIDQ2948115zbMATH OpenOpenAlexFDO

Authors XiaoLong Zou, Xianping Guo

Publication date 29 September 2015

Published in Kybernetika (Search for Journal in Brave)

Full work available at URL http://hdl.handle.net/10338.dmlcz/144298

zbMATH Keywords

optimal stationary policydiscrete-time Markov decision processesaverage reward criterionLyapunov-type conditionunbounded reward/cost function

Mathematics Subject Classification ID

Markov and semi-Markov decision processes (90C40) Optimal stochastic control (93E20)

Recommendations

• Average optimality for Markov decision processes in borel spaces: a new condition and approach
• New average optimality conditions for semi-Markov decision processes in Borel spaces
• scientific article; zbMATH DE number 825217
• Verifiable conditions for average optimality of continuous-time Markov decision processes
• On structural properties of optimal average cost functions in Markov decision processes with Borel spaces and universally measurable policies

Cites work

• scientific article; zbMATH DE number 3122709 (Why is no real title available?)
• scientific article; zbMATH DE number 46578 (Why is no real title available?)
• scientific article; zbMATH DE number 1233798 (Why is no real title available?)
• scientific article; zbMATH DE number 1325008 (Why is no real title available?)
• scientific article; zbMATH DE number 1786117 (Why is no real title available?)
• scientific article; zbMATH DE number 5685899 (Why is no real title available?)
• Average cost Markov control processes with weighted norms: existence of canonical policies
• Average optimality for Markov decision processes in borel spaces: a new condition and approach
• Average optimality for continuous-time Markov decision processes with a policy iteration approach
• Discrete-Time Controlled Markov Processes with Average Cost Criterion: A Survey
• Geometric Convergence Rates for Stochastically Ordered Markov Chains
• Limiting average criteria for nonstationary Markov decision processes
• Markov Chains and Stochastic Stability
• Nondiscounted Continuous Time Markovian Decision Process with Countable State Space

Cited in

(5)

• New average optimality conditions for semi-Markov decision processes in Borel spaces
• First passage risk probability optimality for continuous time Markov decision processes
• Verifiable conditions for average optimality of continuous-time Markov decision processes
• Average cost optimality inequality for Markov decision processes with Borel spaces and universally measurable policies
• Average optimality for Markov decision processes in borel spaces: a new condition and approach

This page was built for publication: Another set of verifiable conditions for average Markov decision processes with Borel spaces.

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2948115)