Dynamic programming for variable discounted Markov decision problems

We study the existence of optimal strategies and value function of non stationary Markov decision processes under variable discounted criteria, when the action space is assumed to be Borel and the action space to be compact. With this new way of defining the value of a policy, we show existence of M...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Della Vecchia, Eugenio, Di Marco, Silvia, Vidal, Fernando
Formato: Objeto de conferencia
Lenguaje:Inglés
Publicado: 2014
Materias:
Acceso en línea:http://sedici.unlp.edu.ar/handle/10915/41704
http://43jaiio.sadio.org.ar/proceedings/SIO/17.pdf
Aporte de:
Descripción
Sumario:We study the existence of optimal strategies and value function of non stationary Markov decision processes under variable discounted criteria, when the action space is assumed to be Borel and the action space to be compact. With this new way of defining the value of a policy, we show existence of Markov deterministic optimal policies in the finite-horizon case, and a recursive method to obtain such ones. For the infinite horizon problem we characterize the value function and show existence of stationary deterministic policies. The approach presented is based on the use of adequate dynamic programming operators.