On the Nonexistence of $|varepsilon$-Optimal Randomized Stationary Policies in Average Cost Markov Decision Models

DOI10.1214/AOMS/1177693180zbMath0238.62094OpenAlexW1994602780WikidataQ114846538 ScholiaQ114846538MaRDI QIDQ5649333

Sheldon M. Ross

Publication date: 1971

Published in: The Annals of Mathematical Statistics (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1214/aoms/1177693180

Mathematics Subject Classification ID

Markov processes: estimation; hidden Markov models (62M05)

Related Items (3)

Average Cost Markov Decision Processes with Weakly Continuous Transition Probabilities ⋮ Convex analytic method revisited: further optimality results and performance of deterministic policies in average cost stochastic control ⋮ Long-term average cost control problems for continuous time Markov processes: A survey

This page was built for publication: On the Nonexistence of $|varepsilon$-Optimal Randomized Stationary Policies in Average Cost Markov Decision Models