A framework and a mean-field algorithm for the local control of spatial processes

DOI10.1016/J.IJAR.2011.09.007MaRDI QIDQ433494zbMATH OpenOpenAlexDBLPWikidataFDO

Authors Régis Sabbadin, Nathalie Peyrard, Nicklas Forsell

Publication date 5 July 2012

Published in International Journal of Approximate Reasoning (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1016/j.ijar.2011.09.007

zbMATH Keywords

approximate linear programmingapproximate policy iterationdecision-theoretic planningfactored Markov decision processesmean-field principle

Mathematics Subject Classification ID

Decision theory (91B06) Markov and semi-Markov decision processes (90C40)

Recommendations

• Solving Markov decision processes by \(d\)-graph algorithms
• Influence of modeling structure in probabilistic sequential decision problems
• scientific article; zbMATH DE number 1929153
• A sparse sampling algorithm for near-optimal planning in large Markov decision processes
• A methodology for computation reduction for specially structured large scale Markov decision problems

Cites work

• scientific article; zbMATH DE number 1321699 (Why is no real title available?)
• scientific article; zbMATH DE number 1348599 (Why is no real title available?)
• scientific article; zbMATH DE number 2000828 (Why is no real title available?)
• A computational theory of decision networks
• Advanced mean field methods. Theory and practice
• Control of spatially structured random processes and random fields with applications.
• Management of the risk of wind damage in forestry: a graph-based Markov decision process approach
• On Constraint Sampling in the Linear Programming Approach to Approximate Dynamic Programming
• Optimal control of diffusion processes with reflection
• Solving factored mdps with hybrid state and action variables
• Stochastic dynamic programming with factored representations
• The Linear Programming Approach to Approximate Dynamic Programming

Cited in

(3)

• Reinforcement learning-based design of sampling policies under cost constraints in Markov random fields: application to weed map reconstruction
• Control of spatially structured random processes and random fields with applications.
• Efficient approximate linear programming for factored MDPs

This page was built for publication: A framework and a mean-field algorithm for the local control of spatial processes

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q433494)