Connectedness conditions used in finite state Markov decision processes

DOI10.1016/0022-247X(79)90135-5zbMath0413.90083MaRDI QIDQ599002

Lyn C. Thomas

Publication date: 1979

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

zbMATH Keywords

convergence analysistransition matricesaverage cost criterionconnectedness conditionsexistence of optimal policiesfinite action spacefinite state Markov decision processes

Mathematics Subject Classification ID

Minimax problems in mathematical programming (90C47)

Related Items (1)

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

Cites Work

• Exponential convergence of products of stochastic matrices
• Dynamic programming, Markov chains, and the method of successive approximations
• Technical Note—Improved Conditions for Convergence in Undiscounted Markov Renewal Programming
• The Asymptotic Behavior of Undiscounted Value Iteration in Markov Decision Problems
• Optimal decision procedures for finite Markov chains. Part II: Communicating systems
• On the Iterative Method of Dynamic Programming on a Finite Space Discrete Time Markov Process
• A Note on Memoryless Rules for Controlling Sequential Control Processes
• Denumerable State Markovian Decision Processes-Average Cost Criterion
• A Solution to a Countable System of Equations Arising in Markovian Decision Processes
• Products of Indecomposable, Aperiodic, Stochastic Matrices
• Unnamed Item
• Unnamed Item

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