A K-step look-ahead analysis of value iteration algorithms for Markov decision processes

DOI10.1016/0377-2217(94)00208-8zbMATH Open0913.90261OpenAlexW1996660883MaRDI QIDQ1266643FDOQ1266643

Authors: Meir Herzberg, Uri Yechiali 

Publication date: 31 May 1999

Published in: European Journal of Operational Research (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1016/0377-2217(94)00208-8

Recommendations

• Accelerating Procedures of the Value Iteration Algorithm for Discounted Markov Decision Processes, Based on a One-Step Lookahead Analysis
• Serial and parallel value iteration algorithms for discounted Markov decision processes
• Monotone value iteration for discounted finite Markov decision processes

zbMATH Keywords

value iterationmodified policy iterationadaptive relaxation factordiscounted and undiscounted Markov decision processeslook-ahead analysis

Mathematics Subject Classification ID

Markov and semi-Markov decision processes (90C40)

Cites Work

• A simple technique in Markovian control with applications to resource allocation to resource allocation in communication networks
• Iterative solution of the functional equations of undiscounted Markov renewal programming
• Modified Policy Iteration Algorithms for Discounted Markov Decision Problems
• Computing Optimal Policies for Controlled Tandem Queueing Systems
• The convergence of value iteration in discounted Markov decision processes
• Truncated policy iteration methods
• Action Elimination Procedures for Modified Policy Iteration Algorithms
• A set of successive approximation methods for discounted Markovian decision problems
• Title not available (Why is that?)
• Accelerating Procedures of the Value Iteration Algorithm for Discounted Markov Decision Processes, Based on a One-Step Lookahead Analysis
• Some Bounds for Discounted Sequential Decision Processes
• Branch-and-Bound Strategies for Dynamic Programming
• Bounds and Transformations for Discounted Finite Markov Decision Chains
• Letter to the Editor—A Test for Suboptimal Actions in Markovian Decision Problems
• Criteria for selecting the relaxation factor of the value iteration algorithm for undiscounted Markov and semi-Markov decision processes
• Discrete versions of an algorithm due to Varaiya
• Computational comparison of value iteration algorithms for discounted Markov decision processes
• Technical Note—Accelerated Computation of the Expected Discounted Return in a Markov Chain
• Title not available (Why is that?)
• Technical Note—Undiscounted Markov Renewal Programming Via Modified Successive Approximations
• Title not available (Why is that?)

Cited In (2)

• Accelerated modified policy iteration algorithms for Markov decision processes
• Accelerating Procedures of the Value Iteration Algorithm for Discounted Markov Decision Processes, Based on a One-Step Lookahead Analysis

This page was built for publication: A \(K\)-step look-ahead analysis of value iteration algorithms for Markov decision processes

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1266643)