Computational comparison of value iteration algorithms for discounted Markov decision processes

DOI10.1016/0167-6377(83)90040-8zbMath0511.90094MaRDI QIDQ1839200

Lyn C. Thomas, A. C. Lavercombe, Roger T. Hartley

Publication date: 1983

Published in: Operations Research Letters (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1016/0167-6377(83)90040-8

zbMATH Keywords

bounds; successive over-relaxation; Gauss-Seidel; discounted Markov decision processes; action elimination; computational comparison of value iteration algorithms; elimination of actions; pre-Jacobi

Mathematics Subject Classification ID

65K05: Numerical mathematical programming methods

90C40: Markov and semi-Markov decision processes

Related Items

Computational comparison of policy iteration algorithms for discounted Markov decision processes, A \(K\)-step look-ahead analysis of value iteration algorithms for Markov decision processes, Computational comparison of value iteration algorithms for discounted Markov decision processes, Serial and parallel value iteration algorithms for discounted Markov decision processes, Computing Optimal Policies for Markovian Decision Processes Using Simulation

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Second order bounds for Markov decision processes
• Computational comparison of value iteration algorithms for discounted Markov decision processes
• Bounds and Transformations for Discounted Finite Markov Decision Chains
• Technical Note—Accelerated Computation of the Expected Discounted Return in a Markov Chain
• Discounted Dynamic Programming
• Letter to the Editor—A Test for Suboptimal Actions in Markovian Decision Problems
• Some Bounds for Discounted Sequential Decision Processes