Maximizing the set of recurrent states of an MDP subject to convex constraints

DOI10.1016/J.AUTOMATICA.2014.01.002MaRDI QIDQ462403zbMATH OpenOpenAlexFDO

Authors Nuno C. Martins, Eduardo Arvelo

Publication date 20 October 2014

Published in Automatica (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1016/j.automatica.2014.01.002

zbMATH Keywords

Markov modelsconvex optimizationmaximum entropyoptimal controlMarkov decision problems

Mathematics Subject Classification ID

Empirical decision procedures; empirical Bayes procedures (62C12) Stochastic programming (90C15) Stochastic systems in control theory (general) (93E03) Optimal stochastic control (93E20)

Recommendations

• A convex optimization approach to dynamic programming in continuous state and action spaces
• Constrained denumerable state non-stationary MDPs with expected total reward criterion
• A constrained optimization problem with applications to constrained MDPs
• Convex dynamic programming with (bounded) recursive utility
• Convex Optimization for Parameter Synthesis in MDPs
• On the relationship between the maximum principle and dynamic programming under state constraints
• Maximizing a state convex Lagrange functional in optimal control
• Dynamic programming in constrained Markov decision processes
• Constrained Markovian decision processes: The dynamic programming approach

Cites work

• scientific article; zbMATH DE number 4160608 (Why is no real title available?)
• scientific article; zbMATH DE number 5542185 (Why is no real title available?)
• scientific article; zbMATH DE number 1348599 (Why is no real title available?)
• scientific article; zbMATH DE number 700091 (Why is no real title available?)
• scientific article; zbMATH DE number 1786123 (Why is no real title available?)
• A probabilistic language formalism for stochastic discrete-event systems
• Controlled Markov chains with constraints.
• Controlled Markov chains with safety upper bound
• Discrete-Time Controlled Markov Processes with Average Cost Criterion: A Survey
• Dynamic programming and optimal control. Vol. 1.
• Information Theory and Statistics: A Tutorial
• Linear Programming and Markov Decision Chains
• Linear Programming in a Markov Chain
• Markov Renewal Programming by Linear Fractional Programming

Describes a project that uses

Uses Software

• CVX

This page was built for publication: Maximizing the set of recurrent states of an MDP subject to convex constraints

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q462403)