A Policy Improvement Method in Constrained Stochastic Dynamic Programming

DOI10.1109/TAC.2006.880801MaRDI QIDQ5281937zbMATH OpenFDO

Authors Hyeong Soo Chang

Publication date 27 July 2017

Published in IEEE Transactions on Automatic Control (Search for Journal in Brave)

Mathematics Subject Classification ID

Dynamic programming (90C39) Markov and semi-Markov decision processes (90C40)

Recommendations

• A policy improvement method for constrained average Markov decision processes
• Random search for constrained Markov decision processes with multi-policy improvement
• A stochastic improvement method for stochastic programming
• Improving the performance of stochastic dual dynamic programming
• Constrained Undiscounted Stochastic Dynamic Programming
• On the policy improvement algorithm in continuous time
• Computing average optimal constrained policies in stochastic dynamic programming.
• An efficient policy iteration algorithm for dynamic programming equations

Cited in

(9)

• On Bellman's principle with inequality constraints
• A Class of Decision Processes Showing Policy-Improvement/Newton–Raphson Equivalence
• An exact iterative search algorithm for constrained Markov decision processes
• A policy iteration heuristic for constrained discounted controlled Markov chains
• Constrained Markov decision processes in Borel spaces: from discounted to average optimality
• Random search for constrained Markov decision processes with multi-policy improvement
• Resource-constrained management of heterogeneous assets with stochastic deterioration
• Improved order 1/4 convergence for piecewise constant policy approximation of stochastic control problems
• A policy improvement method for constrained average Markov decision processes

This page was built for publication: A Policy Improvement Method in Constrained Stochastic Dynamic Programming

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5281937)