Connectedness conditions used in finite state Markov decision processes

DOI10.1016/0022-247X(79)90135-5zbMATH Open0413.90083MaRDI QIDQ599002FDOQ599002

Authors: Lyn C. Thomas Edit this on Wikidata

Publication date: 1979

Published in: Journal of Mathematical Analysis and Applications (Search for Journal in Brave)

zbMATH Keywords

transition matricesconvergence analysisaverage cost criterionconnectedness conditionsexistence of optimal policiesfinite action spacefinite state Markov decision processes

Mathematics Subject Classification ID

Minimax problems in mathematical programming (90C47)

Cites Work

• Title not available (Why is that?)
• Dynamic programming, Markov chains, and the method of successive approximations
• The Asymptotic Behavior of Undiscounted Value Iteration in Markov Decision Problems
• A Note on Memoryless Rules for Controlling Sequential Control Processes
• Products of Indecomposable, Aperiodic, Stochastic Matrices
• Denumerable State Markovian Decision Processes-Average Cost Criterion
• Optimal decision procedures for finite Markov chains. Part II: Communicating systems
• A Solution to a Countable System of Equations Arising in Markovian Decision Processes
• Exponential convergence of products of stochastic matrices
• Title not available (Why is that?)
• Technical Note—Improved Conditions for Convergence in Undiscounted Markov Renewal Programming
• On the Iterative Method of Dynamic Programming on a Finite Space Discrete Time Markov Process

Cited In (1)

• A note on the vanishing interest rate approach in average Markov decision chains with continuous and bounded costs

This page was built for publication: Connectedness conditions used in finite state Markov decision processes

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q599002)