The method of value oriented successive approximations for the average reward Markov decision process

DOI10.1007/BF01719500zbMath0443.90109OpenAlexW2123114919MaRDI QIDQ1144501

S. H. Smith

Publication date: 1980

Published in: OR Spektrum (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1007/bf01719500

zbMATH Keywords

convergenceaverage rewardfinite action spacefinite state spacealmost optimal solutionsvalue oriented successive approximations

Mathematics Subject Classification ID

Numerical mathematical programming methods (65K05) Markov and semi-Markov decision processes (90C40)

Related Items

The numerical exploitation of periodicity in Markov decision processes, A value iteration method for undiscounted multichain Markov decision processes, MARKOV DECISION PROCESSES

Cites Work

• A successive approximation algorithm for an undiscounted Markov decision process
• Dynamic programming, Markov chains, and the method of successive approximations
• Iterative solution of the functional equations of undiscounted Markov renewal programming
• Discounting, Ergodicity and Convergence for Markov Decision Processes
• A set of successive approximation methods for discounted Markovian decision problems
• Technical Note—Improved Conditions for Convergence in Undiscounted Markov Renewal Programming
• Geometric convergence of value-iteration in multichain Markov decision problems
• The Asymptotic Behavior of Undiscounted Value Iteration in Markov Decision Problems
• Optimal decision procedures for finite Markov chains. Part II: Communicating systems
• Technical Note—The Method of Successive Approximations and Markovian Decision Problems
• On Finding the Maximal Gain for Markov Decision Processes
• Technical Note—Bounds on the Gain of a Markov Decision Process
• Technical Note—Undiscounted Markov Renewal Programming Via Modified Successive Approximations
• Some Bounds for Discounted Sequential Decision Processes
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item