Singularly perturbed linear programs and Markov decision processes

DOI10.1016/j.orl.2016.02.005zbMath1410.90236arXiv1611.07388OpenAlexW2279989366MaRDI QIDQ1790182

Andrew Stillman, Jerzy A. Filar, Vladimir Gaitsgory, Konstantin E. Avrachenkov

Publication date: 2 October 2018

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

Full work available at URL: https://arxiv.org/abs/1611.07388

zbMATH Keywords

Markov decision processes (MDPs)discounted MDPslimiting linear programlong-run average MDPssingularly perturbed linear programs

Mathematics Subject Classification ID

Linear programming (90C05) Markov and semi-Markov decision processes (90C40)

Related Items (1)

LP based upper and lower bounds for Cesàro and Abel limits of the optimal values in problems of control of stochastic discrete time systems

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Sensitivity analysis in discounted Markovian decision problems
• Asymptotic linear programming and policy improvement for singularly perturbed Markov decision processes
• An asymptotic simplex method for singularly perturbed linear programs
• Constraint augmentation in pseudo-singularly perturbed linear programs
• Inversion of Analytic Matrix Functions That are Singular at the Origin
• Linear Programming and Sequential Decisions
• Analytic Perturbation Theory and Its Applications
• Constrained Undiscounted Stochastic Dynamic Programming
• Linear Programming and Markov Decision Chains
• Asymptotic Linear Programming
• Discrete Dynamic Programming
• On Finding Optimal Policies in Discrete Dynamic Programming with No Discounting
• Discrete Dynamic Programming with Sensitive Discount Optimality Criteria

This page was built for publication: Singularly perturbed linear programs and Markov decision processes