Semi-Markovian decision models with vector-valued reward

Autor:	V. Nollau, G. Döge
Rok vydání:	1995
Předmět:	Mathematical optimization Control and Optimization Applied Mathematics Decision tree Partially observable Markov decision process Influence diagram Markov decision process Decision rule Management Science and Operations Research Markov model Decision model Mathematics Optimal decision
Zdroj:	Optimization. 34:247-259
ISSN:	1029-4945 0233-1934
DOI:	10.1080/02331939508844110
Popis:	The paper deals with vector-valued semi-Markovian decision process (VSMDP). Thereby we derive a suitable definition of the optimal average reward of a VSMDP. We construct an algorithm for improving policies in the vector-valued case.
Databáze:	OpenAIRE
Externí odkaz:	https://explore.openaire.eu/search/publication?articleId=doi_________::6774964885da26a34bae76a0ae6409cf https://doi.org/10.1080/02331939508844110 Zobrazit plný text záznamu