Markov Strategies in Dynamic Programming

Autor: van Km Kees Hee
Rok vydání: 1978
Předmět:
Zdroj: Mathematics of Operations Research. 3:37-41
ISSN: 1526-5471
0364-765X
DOI: 10.1287/moor.3.1.37
Popis: It is shown that the supremum of the expected total return over the Markov strategies equals the supremum over all strategies. The model assumptions are: the state space is countable, the action space is measurable and the supremum of the expected total of the positive rewards over the Markov strategies is finite.
Databáze: OpenAIRE