scientific article; zbMATH DE number 934465

MaRDI QIDQ4895162zbMATH OpenFDO

Authors Shaler jun. Stidham

Publication date 13 October 1996

zbMATH Keywords

discrete-time Markov decision processexpected total rewardgeneral state and action spacesemi-Markovian decision processesstopping problems

Mathematics Subject Classification ID

Markov and semi-Markov decision processes (90C40)

Recommendations

• Finite state approximations for denumerable state infinite horizon discounted Markov decision processes with unbounded rewards
• Reward Revision for Discounted Markov Decision Problems
• scientific article; zbMATH DE number 4112513
• On the expected total reward with unbounded returns for Markov decision processes
• Markov decision processes with state-dependent discount factors and unbounded rewards/costs

Cited in

(4)

• On the expected total reward with unbounded returns for Markov decision processes
• scientific article; zbMATH DE number 3950237 (Why is no real title available?)
• Successive Approximations for Finite Horizon, Semi-Markov Decision Processes with Application to Asset Liquidation
• (Approximate) iterated successive approximations algorithm for sequential 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 Q4895162)