A Rollout Algorithm for Multichain Markov Decision Processes with Average Cost

DOI10.1007/978-3-642-02894-6_15MaRDI QIDQ3407649zbMATH OpenOpenAlexFDO

Authors Tao Sun, Peter B. Luh, Qianchuan Zhao

Publication date 4 March 2010

Published in Positive Systems (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1007/978-3-642-02894-6_15

Mathematics Subject Classification ID

Markov and semi-Markov decision processes (90C40) Large-scale systems (93A15)

Recommendations

• scientific article; zbMATH DE number 3854831
• An Algorithm to Identify and Compute Average Optimal Policies in Multichain Markov Decision Processes
• On Average Reward Semi-Markov Decision Processes with a General Multichain Structure
• Average Reward Markov Decision Processes with Multiple Cost Constraints
• scientific article; zbMATH DE number 2030016
• Vector-valued Markov decision processes with average reward criterion: the multichain case
• scientific article; zbMATH DE number 3900546
• scientific article; zbMATH DE number 1500200

Cited in

(2)

• NDP methods for multi-chain MDPs
• An Algorithm to Identify and Compute Average Optimal Policies in Multichain Markov Decision Processes

This page was built for publication: A Rollout Algorithm for Multichain Markov Decision Processes with Average Cost

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q3407649)