Computation techniques for large scale undiscounted markov decision processes

DOI10.1002/nav.3800260404zbMath0497.90078OpenAlexW1584686897MaRDI QIDQ3962809

Gary J. Koehler, Thom J. Hodgson

Publication date: 1979

Published in: Naval Research Logistics Quarterly (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1002/nav.3800260404

zbMATH Keywords

convergence ratesuccessive approximation procedurecomputation techniqueslarge scale undiscounted Markov decision processesproper scale factor selectionWhite procedure

Mathematics Subject Classification ID

Markov and semi-Markov decision processes (90C40) Numerical methods for mathematical programming, optimization and variational techniques (65K99)

Related Items (1)

A methodology for computation reduction for specially structured large scale Markov decision problems

Cites Work

• Unnamed Item
• Dynamic programming, Markov chains, and the method of successive approximations
• A modified dynamic programming method for Markovian decision problems
• Iterative solution of the functional equations of undiscounted Markov renewal programming
• Erratum—Tests for Suboptimal Actions in Discounted Markov Programming
• Bounds and Transformations for Discounted Finite Markov Decision Chains
• Note—A Test for Nonoptimal Actions in Undiscounted Finite Markov Decision Chains
• Discounting, Ergodicity and Convergence for Markov Decision Processes
• Technical Note—Improved Conditions for Convergence in Undiscounted Markov Renewal Programming
• Technical Note—The Method of Successive Approximations and Markovian Decision Problems
• Markov-Renewal Programming. I: Formulation, Finite Return Models
• Letter to the Editor—A Test for Suboptimal Actions in Markovian Decision Problems
• On Finding the Maximal Gain for Markov Decision Processes
• Technical Note—On the Asymptotic Convergence Rate of Cost Differences for Markovian Decision Processes
• Some Bounds for Discounted Sequential Decision Processes
• Generalization of White's Method of Successive Approximations to Periodic Markovian Decision Processes
• Tests for Suboptimal Actions in Discounted Markov Programming
• Multiple Policy Improvements in Undiscounted Markov Renewal Programming

This page was built for publication: Computation techniques for large scale undiscounted markov decision processes