Normalized Markov Decision Chains. II: Optimality of Nonstationary Policies

DOI10.1137/0315016zbMath0367.90118OpenAlexW2083534744MaRDI QIDQ4145454

Uriel G. Rothblum

Publication date: 1977

Published in: SIAM Journal on Control and Optimization (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1137/0315016

Mathematics Subject Classification ID

Markov and semi-Markov decision processes (90C40)

Related Items (4)

Unnamed Item ⋮ Stability and convergence in discrete convex monotone dynamical systems ⋮ Transient policies in discrete dynamic programming: Linear programming including suboptimality tests and additional constraints ⋮ Generalized eigenvectors and sets of nonnegative matrices

This page was built for publication: Normalized Markov Decision Chains. II: Optimality of Nonstationary Policies