Stationary optimal policies in a class of multichain positive dynamic programs with finite state space and risk-sensitive criterion

• Autorzy: Rolando Cavazos-Cadena , Raul Montes-de-Oca
• Języki publikacji: EN

Abstrakty

EN

This work concerns Markov decision processes with finite state space and compact action sets. The decision maker is supposed to have a constant-risk sensitivity coefficient, and a control policy is graded via the risk-sensitive expected total-reward criterion associated with nonnegative one-step rewards. Assuming that the optimal value function is finite, under mild continuity and compactness restrictions the following result is established: If the number of ergodic classes when a stationary policy is used to drive the system depends continuously on the policy employed, then there exists an optimal stationary policy, extending results obtained by Schal (1984) for risk-neutral dynamic programming. We use results recently established for unichain systems, and analyze the general multichain case via a reduction to a model with the unichain property.

Kategorie tematyczne

• 90C40: Markov and semi-Markov decision processes
• 93E20: Optimal stochastic control

• Wydawca: Institute of Mathematics Polish Academy of Sciences
• Czasopismo: Applicationes Mathematicae
• Rocznik: 2001
• Tom: 28
• Numer: 1
• Strony: 93-109

Daty

wydano

2001

Twórcy

autor

Rolando Cavazos-Cadena

• Departamento de Estadistica y Calculo, Universidad Autonoma Agraria Antonio Narro, Buenavista, Saltillo COAH 25315, Mexico

autor

Raul Montes-de-Oca

• Departamento de Matematicas, Universidad Autonoma Metropolitana, Campus Iztapalapa, Avenida Michoacan y La Purisima s/n, Col. Vicentina, Mexico D.F. 09340, Mexico

Identyfikatory

DOI

10.4064/am28-1-7