A semimartingale characterization of average optimal stationary policies for Markov decision processes

DOI10.1155/JAMSA/2006/81593zbMath1151.90576OpenAlexW2023178539MaRDI QIDQ871336

Xianping Guo, Quanxin Zhu

Publication date: 19 March 2007

Published in: Journal of Applied Mathematics and Stochastic Analysis (Search for Journal in Brave)

Full work available at URL: https://eudml.org/doc/54838

Mathematics Subject Classification ID

Generalizations of martingales (60G48) Optimal stochastic control (93E20) Markov and semi-Markov decision processes (90C40)

Related Items (1)

Maximizing the probability of attaining a target prior to extinction

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Adaptive Markov control processes
• Finite state Markovian decision processes
• Unbounded cost Markov decision processes with limsup and liminf average criteria: new conditions
• Limiting Average Criteria For Nonstationary Markov Decision Processes
• Nonhomogeneous Markov Decision Processes with Borel State Space—The Average Criterion with Nonuniformly Bounded Rewards
• Average optimality for Markov decision processes in borel spaces: a new condition and approach
• Discrete-Time Controlled Markov Processes with Average Cost Criterion: A Survey
• Average cost Markov control processes with weighted norms: existence of canonical policies
• Average Optimality in Markov Control Processes via Discounted-Cost Problems and Linear Programming
• Another Set of Conditions for Strongn(n = −1, 0) Discount Optimality in Markov Decision Processes

This page was built for publication: A semimartingale characterization of average optimal stationary policies for Markov decision processes