A value iteration method for undiscounted multichain Markov decision processes

DOI10.1007/BF01919182zbMATH Open0645.90098MaRDI QIDQ3789375FDOQ3789375

Authors:

Publication date: 1988

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

Recommendations

• Value iteration and approximately optimal stationary policies in finite-state average Markov decision chains
• Value Iteration in a Class of Communicating Markov Decision Chains with the Average Cost Criterion
• scientific article; zbMATH DE number 3854831
• scientific article; zbMATH DE number 970660
• Value iteration in countable state average cost Markov decision processes with unbounded costs

zbMATH Keywords

decompositionvalue iterationsuccessive approximations\(\epsilon \)- optimal policyinfinite horizon average expected reward Markov decision processes

Mathematics Subject Classification ID

Markov and semi-Markov decision processes (90C40)

Cites Work

• Title not available (Why is that?)
• Dynamic programming, Markov chains, and the method of successive approximations
• Title not available (Why is that?)
• The Asymptotic Behavior of Undiscounted Value Iteration in Markov Decision Problems
• Markov Renewal Programs with Small Interest Rates
• Finite state Markovian decision processes
• Iterative solution of the functional equations of undiscounted Markov renewal programming
• Computing Optimal Policies for Controlled Tandem Queueing Systems
• Optimal decision procedures for finite Markov chains. Part III: General convex systems
• On Finding Optimal Policies in Discrete Dynamic Programming with No Discounting
• Linear Programming and Markov Decision Chains
• Multichain Markov Renewal Programs
• On Finding the Maximal Gain for Markov Decision Processes
• Title not available (Why is that?)
• The method of value oriented successive approximations for the average reward Markov decision process
• 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
• A value-iteration scheme for undiscounted multichain Markov renewal programs
• Geometric convergence of value-iteration in multichain Markov decision problems
• Technical Note—Undiscounted Markov Renewal Programming Via Modified Successive Approximations
• Title not available (Why is that?)
• A New Specification of the Multichain Policy Iteration Algorithm in Undiscounted Markov Renewal Programs
• Title not available (Why is that?)
• A further anticycling rule in multichain policy iteration for undiscounted Markov renewal programs

Cited In (13)

• Value iteration and approximately optimal stationary policies in finite-state average Markov decision chains
• On the existence of relative values for undiscounted multichain Markov decision processes
• Title not available (Why is that?)
• A value-iteration scheme for undiscounted multichain Markov renewal programs
• A structured pattern matrix algorithm for multichain Markov decision processes
• Multiplicative Markov Decision Chains
• Optimality of Stationary Halting Policies and Finite Termination of Successive Approximations
• Title not available (Why is that?)
• On the Convergence of Policy Iteration in Finite State Undiscounted Markov Decision Processes: The Unichain Case
• Posterior bounds on the equilibrium distribution of a finite markov chain
• Title not available (Why is that?)
• Technical Note—Successive Approximations in Value Determination for a Markov Decision Process
• Vector-valued Markov decision processes with average reward criterion: the multichain case

This page was built for publication: A value iteration method for undiscounted multichain Markov decision processes

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q3789375)