Nonhomogeneous Markov Decision Processes with Borel State Space—The Average Criterion with Nonuniformly Bounded Rewards

DOI10.1287/moor.25.4.667.12119zbMath1073.90569OpenAlexW2116517792MaRDI QIDQ2757659

Jianyong Liu, Ke Liu, Xianping Guo

Publication date: 26 November 2001

Published in: Mathematics of Operations Research (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1287/moor.25.4.667.12119

zbMATH Keywords

nonhomogeneous markov decision processes, average reward criterion, optimality equations, \(\varepsilon(\geq0)\)-optimal policies, rolling horizon algorithm

Mathematics Subject Classification ID

Markov and semi-Markov decision processes (90C40)

Related Items (7)

A semimartingale characterization of average optimal stationary policies for Markov decision processes ⋮ First passage problems for nonstationary discrete-time stochastic control systems ⋮ Controlled Markov decision processes with AVaR criteria for unbounded costs ⋮ Nonstationary discrete-time deterministic and stochastic control systems with infinite horizon ⋮ Average optimality for Markov decision processes in borel spaces: a new condition and approach ⋮ Minimax control for discrete-time time-varying stochastic systems ⋮ Notes on average Markov decision processes with a minimum-variance criterion

This page was built for publication: Nonhomogeneous Markov Decision Processes with Borel State Space—The Average Criterion with Nonuniformly Bounded Rewards