Random search for constrained Markov decision processes with multi-policy improvement

DOI10.1016/J.AUTOMATICA.2015.05.016MaRDI QIDQ895275zbMATH OpenOpenAlexFDO

Authors Hyeong Soo Chang

Publication date 26 November 2015

Published in Automatica (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1016/j.automatica.2015.05.016

zbMATH Keywords

constrained optimizationMarkov decision processesrandom searchpolicy improvement

Mathematics Subject Classification ID

Markov and semi-Markov decision processes (90C40) Optimal stochastic control (93E20)

Recommendations

• Randomized and Past-Dependent Policies for Markov Decision Processes with Multiple Constraints
• A policy improvement method for constrained average Markov decision processes
• Non-randomized policies for constrained Markov decision processes
• An exact iterative search algorithm for constrained Markov decision processes
• A Policy Improvement Method in Constrained Stochastic Dynamic Programming
• Gradient based policy optimization of constrained Markov decision processes
• scientific article; zbMATH DE number 4088775
• An actor-critic algorithm for constrained Markov decision processes
• On the Complexity of the Policy Improvement Algorithm for Markov Decision Processes
• scientific article; zbMATH DE number 3852821

Cites work

• scientific article; zbMATH DE number 700091 (Why is no real title available?)
• A Policy Improvement Method in Constrained Stochastic Dynamic Programming
• A solving method of an MDP with a constraint by genetic algorithms.
• A survey of computational complexity results in systems and control
• An exact iterative search algorithm for constrained Markov decision processes
• Constrained discounted Markov decision processes and Hamiltonian cycles.
• Dynamic Programming Equations for Discounted Constrained Stochastic Control
• Encyclopedia of Optimization
• Introduction to Stochastic Search and Optimization
• Non-randomized policies for constrained Markov decision processes
• Notes on the Scenario Design Approach
• Policy set iteration for Markov decision processes
• Simulated annealing with asymptotic convergence for nonlinear constrained optimization
• Simulation-based algorithms for Markov decision processes
• The simplex and policy-iteration methods are strongly polynomial for the Markov decision problem with a fixed discount rate

Cited in

(4)

• A pseudo-polynomial heuristic for path-constrained discrete-time Markovian-target search
• A Policy Improvement Method in Constrained Stochastic Dynamic Programming
• Markov decision processes with burstiness constraints
• An exact iterative search algorithm for constrained Markov decision processes

This page was built for publication: Random search for constrained Markov decision processes with multi-policy improvement

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q895275)