scientific article

From MaRDI portal

Publication:3661341

Jump to:navigation, search

zbMath0514.90085MaRDI QIDQ3661341

Dieter Kadelka

Publication date: 1983

Title: zbMATH Open Web Interface contents unavailable due to conflicting licenses.

zbMATH Keywords

average reward integral representation theorem total expected reward Markovian decision model dynamic programming with Borel state and action space infinite future mixtures of deterministic policies randomized Markovian policy

Mathematics Subject Classification ID

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

Related Items

Stochastic scheduling problems I — General strategies

Retrieved from "https://portal.mardi4nfdi.de/w/index.php?title=Publication:3661341&oldid=17125451"