Uniqueness of optimal policies as a generic property of discounted Markov decision processes: Ekeland's variational principle approach

DOI10.14736/KYB-2016-1-0066zbMath1374.90407OpenAlexW2313565647MaRDI QIDQ2798089

Raúl Montes-De-oca, Israel R. Ortega-Gutiérrez, Enrique Lemus-Rodríguez

Publication date: 1 April 2016

Published in: Kybernetika (Search for Journal in Brave)

Full work available at URL: http://hdl.handle.net/10338.dmlcz/144863

zbMATH Keywords

dynamic programmingEkeland's variational principlediscounted Markov decision processesnon-uniqueness of optimal policiesunique optimal policy

Mathematics Subject Classification ID

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

This page was built for publication: Uniqueness of optimal policies as a generic property of discounted Markov decision processes: Ekeland's variational principle approach