Average cost Markov decision processes: Optimality conditions

DOI10.1016/0022-247X(91)90244-TzbMath0739.90072MaRDI QIDQ1176301

Jean-Bernard Lasserre, Jean Claude Hennet, Onésimo Hernández-Lerma

Publication date: 25 June 1992

Published in: Journal of Mathematical Analysis and Applications (Search for Journal in Brave)

zbMATH Keywords

duality theoremopportunity costergodicity conditionsstrong average optimalitylong run expected average cost criterion

Mathematics Subject Classification ID

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

Related Items

A partial history of the early development of continuous-time nonlinear stochastic systems theory ⋮ Recurrence conditions for Markov decision processes with Borel state space: A survey ⋮ Value iteration in average cost Markov control processes on Borel spaces ⋮ The LP approach in average reward MDPs with multiple cost constraints: The countable state case ⋮ On strong average optimality of Markov decision processes with unbounded costs ⋮ Remarks on the existence of solutions to the average cost optimality equation in Markov decision processes ⋮ Numerical comparison of controls and verification of optimality for stochastic control problems

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Optimal steady states, excessive functions, and deterministic dynamic programs
• A forecast horizon and a stopping rule for general Markov decision processes
• Communicating MDPs: Equivalence and LP properties
• On optimality criteria for dynamic programs with long finite horizons
• Duality theorem in Markovian decision problems
• Adaptive Markov control processes
• Recurrence conditions for Markov decision processes with Borel state space: A survey
• The Existence of a Minimum Pair of State and Policy for Markov Decision Processes under the Hypothesis of Doeblin