Variational characterizations in Markov decision processes

DOI10.1016/0022-247X(86)90229-5zbMath0594.90088MaRDI QIDQ1077334

Paul J. Schweitzer, Awi Federgruen

Publication date: 1986

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

zbMATH Keywords

discounted and undiscounted semi-Markov decision processesVariational characterizations

Mathematics Subject Classification ID

Linear programming (90C05) Markov renewal processes, semi-Markov processes (60K15) Markov and semi-Markov decision processes (90C40)

Related Items (2)

Bounds on the fixed point of a monotone contraction operator ⋮ Contraction mappings underlying undiscounted Markov decision problems

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• On the solvability of Bellman's functional equations for Markov renewal programming
• A modified dynamic programming method for Markovian decision problems
• Iterative solution of the functional equations of undiscounted Markov renewal programming
• On the solvability of Bellman's functional equation for a Markovian decision process
• Successive Approximation Methods for Solving Nested Functional Equations in Markov Decision Problems
• Linear Programming and Markov Decision Chains
• A UNIFIED APPROACH TO ALGORITHMS WITH A SUBOPTIMALITY TEST IN DISCOUNTED SEMI-MARKOV DECISION PROCESSES
• Action Elimination Procedures for Modified Policy Iteration Algorithms
• Note—A Test for Nonoptimal Actions in Undiscounted Finite Markov Decision Chains
• The Functional Equations of Undiscounted Markov Renewal Programming
• Geometric convergence of value-iteration in multichain Markov decision problems
• Markov-Renewal Programming. I: Formulation, Finite Return Models
• Contraction Mappings in the Theory Underlying Dynamic Programming
• Letter to the Editor—A Test for Suboptimal Actions in Markovian Decision Problems
• Discrete Dynamic Programming with a Small Interest Rate
• Discrete Dynamic Programming with Sensitive Discount Optimality Criteria
• On Finding the Maximal Gain for Markov Decision Processes
• Perturbation theory and finite Markov chains
• Multichain Markov Renewal Programs
• Technical Note—Bounds on the Gain of a Markov Decision Process
• Some Bounds for Discounted Sequential Decision Processes
• Markov Renewal Programs with Small Interest Rates
• Tests for Suboptimal Actions in Discounted Markov Programming
• Technical Note—Elimination of Suboptimal Actions in Markov Decision Problems
• Potentials for denumerable Markov chains

This page was built for publication: Variational characterizations in Markov decision processes