Accelerating Procedures of the Value Iteration Algorithm for Discounted Markov Decision Processes, Based on a One-Step Lookahead Analysis

DOI10.1287/opre.42.5.940zbMath0823.90132OpenAlexW2100764713MaRDI QIDQ4319773

Meir Herzberg, Uri Yechiali

Publication date: 6 February 1995

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

Full work available at URL: https://semanticscholar.org/paper/268b5f709d2af3d4024a21eaf49c3fb6c369b454

zbMATH Keywords

finite state, stationary, infinite horizon Markov decision process

Mathematics Subject Classification ID

Sequential statistical methods (62L99) Markov and semi-Markov decision processes (90C40)

Related Items (4)

Accelerated modified policy iteration algorithms for Markov decision processes ⋮ The stochastic economic lot sizing problem for non-stop multi-grade production with sequence-restricted setup changeovers ⋮ Value set iteration for Markov decision processes ⋮ A \(K\)-step look-ahead analysis of value iteration algorithms for Markov decision processes

This page was built for publication: Accelerating Procedures of the Value Iteration Algorithm for Discounted Markov Decision Processes, Based on a One-Step Lookahead Analysis