Communicating MDPs: Equivalence and LP properties

DOI10.1016/0167-6377(88)90062-4zbMath0659.90095OpenAlexW2070266110MaRDI QIDQ1112741

Todd A. Schultz, Jerzy A. Filar

Publication date: 1988

Published in: Operations Research Letters (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1016/0167-6377(88)90062-4

zbMATH Keywords

irreducible Markov chain

Mathematics Subject Classification ID

Linear programming (90C05) Markov chains (discrete-time Markov processes on discrete state spaces) (60J10) Markov and semi-Markov decision processes (90C40)

Related Items (7)

An improved algorithm for solving communicating average reward Markov decision processes ⋮ On some algorithms for limiting average Markov decision processes ⋮ Survey of linear programming for standard and nonstandard Markovian control problems. Part I: Theory ⋮ Derman's book as inspiration: some results on LP for MDPs ⋮ A decomposition algorithm for limiting average Markov decision problems. ⋮ Average cost Markov decision processes: Optimality conditions ⋮ Finite state Markov decision models with average reward criteria

Cites Work

• Unnamed Item
• Finite state Markovian decision processes
• Linear Programming and Sequential Decisions
• Linear Programming and Markov Decision Chains
• Optimal decision procedures for finite Markov chains. Part II: Communicating systems
• Discrete Dynamic Programming
• On Linear Programming in a Markov Decision Problem
• Computing a Bias-Optimal Policy in a Discrete-Time Markov Decision Problem
• Multichain Markov Renewal Programs

This page was built for publication: Communicating MDPs: Equivalence and LP properties