Non-randomized policies for constrained Markov decision processes

DOI10.1007/s00186-006-0133-xzbMath1126.90074OpenAlexW2069873069MaRDI QIDQ2466782

Richard C. Chen, Eugene A. Feinberg

Publication date: 16 January 2008

Published in: Mathematical Methods of Operations Research (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1007/s00186-006-0133-x

zbMATH Keywords

Dynamic programmingDecision processesConstrained MarkovNon-randomized policies

Mathematics Subject Classification ID

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

Related Items (11)

Constrained optimality for finite horizon semi-Markov decision processes in Polish spaces ⋮ A mean-variance optimization problem for discounted Markov decision processes ⋮ Random search for constrained Markov decision processes with multi-policy improvement ⋮ Sleeping experts and bandits approach to constrained Markov decision processes ⋮ On Bellman's principle with inequality constraints ⋮ An exact iterative search algorithm for constrained Markov decision processes ⋮ Discounted continuous-time constrained Markov decision processes in Polish spaces ⋮ Constrained Markov decision processes in Borel spaces: from discounted to average optimality ⋮ Compactness of the space of non-randomized policies in countable-state sequential decision processes ⋮ Constrained discounted Markov decision processes with Borel state spaces ⋮ Resource-constrained management of heterogeneous assets with stochastic deterioration

Cites Work

• Sensitivity of constrained Markov decision processes
• Constrained Markovian decision processes: The dynamic programming approach
• Mixed risk-neutral/minimax control of discrete-time, finite-state Markov decision processes
• Dynamic Programming Equations for Discounted Constrained Stochastic Control

This page was built for publication: Non-randomized policies for constrained Markov decision processes