Truncated policy iteration methods

DOI10.1016/0167-6377(84)90054-3zbMath0567.90097OpenAlexW1999380740MaRDI QIDQ1060136

Ron S. Dembo, Moshe Haviv

Publication date: 1984

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

Full work available at URL: https://doi.org/10.1016/0167-6377(84)90054-3

zbMATH Keywords

Markov chainsmodified policy iteration methodspreassigned rate-of- convergence

Mathematics Subject Classification ID

Numerical mathematical programming methods (65K05) Stochastic programming (90C15) Dynamic programming (90C39) Markov and semi-Markov decision processes (90C40)

Related Items

Hierarchic Markov processes and their applications in replacement models ⋮ (Approximate) iterated successive approximations algorithm for sequential decision processes ⋮ A \(K\)-step look-ahead analysis of value iteration algorithms for Markov decision processes

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Inexact Newton Methods
• Modified Policy Iteration Algorithms for Discounted Markov Decision Problems
• Contraction Mappings in the Theory Underlying Dynamic Programming