Invariant problems in dynamic programming - average reward criterion

DOI10.1016/0304-4149(80)90014-9MaRDI QIDQ1145070zbMATH OpenOpenAlexFDO

Authors David Assaf

Publication date 1980

Published in Stochastic Processes and their Applications (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1016/0304-4149(80)90014-9

zbMATH Keywords

finite action spaceaverage reward criterionarbitrary state spacebeta-optimal policyinvariant problem

Mathematics Subject Classification ID

Dynamic programming (90C39)

Cites work

• scientific article; zbMATH DE number 3148886 (Why is no real title available?)
• A Solution to a Countable System of Equations Arising in Markovian Decision Processes
• Arbitrary State Markovian Decision Processes
• Averaging vs. discounting in dynamic programming: a counterexample
• Denumerable State Markovian Decision Processes-Average Cost Criterion
• Discounted Dynamic Programming
• Discrete Dynamic Programming
• Invariant problems in discounted dynamic programming
• Linear programming and sequential decisions
• Markovian Sequential Replacement Processes
• Negative Dynamic Programming
• Non-Discounted Denumerable Markovian Decision Models

Cited in

(5)

• Robust Markov control processes
• A note on risk-sensitive control of invariant models
• Average cost optimality inequality for Markov decision processes with Borel spaces and universally measurable policies
• Recurrence conditions for Markov decision processes with Borel state space: A survey
• Controlled semi-Markov models under long-run average rewards

This page was built for publication: Invariant problems in dynamic programming - average reward criterion

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1145070)