Existence of optimal stationary policies in discounted Markov decision processes: Approaches by occupation measures
From MaRDI portal
Publication:1327188
DOI10.1016/0898-1221(94)90128-7zbMath0799.90119OpenAlexW1964720514MaRDI QIDQ1327188
Publication date: 15 June 1994
Published in: Computers \& Mathematics with Applications (Search for Journal in Brave)
Full work available at URL: https://doi.org/10.1016/0898-1221(94)90128-7
bounded Borel measurable cost functionsgeneral state and action spacesoptimal stationary Borel measurable policies
Cites Work
- Unnamed Item
- Unnamed Item
- A convex analytic approach to Markov decision processes
- Stochastic optimal control. The discrete time case
- Average cost Markov decision processes under the hypothesis of Doeblin
- Probability Measures on Compact Sets
- The Existence of a Minimum Pair of State and Policy for Markov Decision Processes under the Hypothesis of Doeblin
- Discounted Dynamic Programming
- Negative Dynamic Programming
- Letter to the Editor—Age Replacement with Discounting
- Non-Existence of Everywhere Proper Conditional Distributions
This page was built for publication: Existence of optimal stationary policies in discounted Markov decision processes: Approaches by occupation measures