Invariant problems in dynamic programming - average reward criterion

DOI10.1016/0304-4149(80)90014-9zbMath0444.90102OpenAlexW2003480407MaRDI QIDQ1145070

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

average reward criterionfinite action spacearbitrary state spacebeta-optimal policyinvariant problem

Mathematics Subject Classification ID

Dynamic programming (90C39)

Related Items (5)

A note on risk-sensitive control of invariant models ⋮ Recurrence conditions for Markov decision processes with Borel state space: A survey ⋮ Robust Markov control processes ⋮ Average Cost Optimality Inequality for Markov Decision Processes with Borel Spaces and Universally Measurable Policies ⋮ Controlled semi-Markov models under long-run average rewards

Cites Work

• Unnamed Item
• Averaging vs. discounting in dynamic programming: a counterexample
• Linear Programming and Sequential Decisions
• Invariant problems in discounted dynamic programming
• Discrete Dynamic Programming
• Discounted Dynamic Programming
• Markovian Sequential Replacement Processes
• Denumerable State Markovian Decision Processes-Average Cost Criterion
• Negative Dynamic Programming
• Non-Discounted Denumerable Markovian Decision Models
• A Solution to a Countable System of Equations Arising in Markovian Decision Processes
• Arbitrary State Markovian Decision Processes

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