An evolutionary random policy search algorithm for solving Markov decision processes

DOI10.1287/IJOC.1050.0155MaRDI QIDQ2892321zbMATH OpenOpenAlexWikidataFDO

Authors Jiaqiao Hu, Michael C. Fu, Vahid R. Ramezani, Steven I. Marcus

Publication date 18 June 2012

Published in INFORMS Journal on Computing (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1287/ijoc.1050.0155

zbMATH Keywords

dynamic programmingMarkov finite statenonlinear queues

Mathematics Subject Classification ID

Approximation methods and heuristics in mathematical programming (90C59) Dynamic programming (90C39) Markov and semi-Markov decision processes (90C40)

Recommendations

• A survey of some simulation-based algorithms for Markov decision processes
• Simulation-based algorithms for Markov decision processes.
• Simulation-based algorithms for Markov decision processes
• A variable neighborhood search based algorithm for finite-horizon Markov decision processes
• Randomized linear programming solves the Markov decision problem in nearly linear (sometimes sublinear) time

Cites work

• simannf90

Cited in

(5)

• scientific article; zbMATH DE number 1841982 (Why is no real title available?)
• Preference-based reinforcement learning: evolutionary direct policy search using a preference-based racing algorithm
• A variable neighborhood search based algorithm for finite-horizon Markov decision processes
• Randomized linear programming solves the Markov decision problem in nearly linear (sometimes sublinear) time
• Optimal online learning for nonlinear belief models using discrete priors

Describes a project that uses

Uses Software

• simannf90

This page was built for publication: An evolutionary random policy search algorithm for solving Markov decision processes

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2892321)