Asymptotic linear programming and policy improvement for singularly perturbed Markov decision processes
From MaRDI portal
Publication:1299922
zbMath0949.90093MaRDI QIDQ1299922
Eitan Altman, Konstantin E. Avrachenkov, Jerzy A. Filar
Publication date: 11 December 2000
Published in: Mathematical Methods of Operations Research (Search for Journal in Brave)
Stochastic systems and control (93E99) Linear programming (90C05) Markov and semi-Markov decision processes (90C40)
Related Items (6)
Computing uniformly optimal strategies in two-player stochastic games ⋮ Asymptotic sign-solvability, multiple objective linear programming, and the nonsubstitution theorem ⋮ Algorithms for uniform optimal strategies in two-player zero-sum stochastic games with perfect information ⋮ The asymptotic optimal partition and extensions of the nonsubstitution theorem ⋮ Singularly perturbed linear programs and Markov decision processes ⋮ An asymptotic simplex method for singularly perturbed linear programs
This page was built for publication: Asymptotic linear programming and policy improvement for singularly perturbed Markov decision processes
