Optimal stationary policies inrisk-sensitive dynamic programs with finite state spaceand nonnegative rewards

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

Abstrakty

EN

This work concerns controlled Markov chains with finite state space and nonnegative rewards; it is assumed that the controller has a constant risk-sensitivity, and that the performance ofa control policy is measured by a risk-sensitive expected total-reward criterion. The existence of optimal stationary policies isstudied within this context, and the main resultestablishes the optimalityof a stationary policy achieving the supremum in the correspondingoptimality equation, whenever the associated Markov chain hasa unique positive recurrent class. Two explicit examples are providedto show that, if such an additional condition fails, an optimal stationarypolicy cannot be generally guaranteed. The results of this note, which consider both the risk-seeking and the risk-averse cases, answer an extended version of a question recently posed in Puterman (1994).

Słowa kluczowe

EN

unichain property; Markov decision processes; risk-sensitive optimality equation; risk-sensitive expected total- reward criterion

• Wydawca: Institute of Mathematics Polish Academy of Sciences
• Czasopismo: Applicationes Mathematicae
• Rocznik: 2000
• Tom: 27
• Numer: 2
• Strony: 167-185

Daty

wydano

2000

otrzymano

1999-04-20

poprawiono

1999-10-05

Twórcy

autor

Rolando Cavazos-Cadena

• Departamento de Estadísticay Cálculo, Universidad Autónoma Agraria Antonio Narro, Buenavista, Saltillo COAH 25315, México

autor

Raúl Montes-de-Oca

• Departamento de Matemáticas, Universidad Autónoma Metropolitana, Campus Iztapalapa, Avenida Michoacán y La Purísima s/n, Col. Vicentina, México, D.F. 09340, México

Bibliografia

• M. G. Ávila-Godoy (1998), Controlled Markov chains with exponentialrisk-sensitive criteria: modularity, structured policies and applications, Ph.D. Dissertation, Dept. of Math., Univ. ofArizona, Tucson, AZ.
• R. Cavazos-Cadena and E. Fernández-Gaucherand (1999), Controlled Markov chains with risk-sensitive criteria:average cost, optimality equations, and optimal solutions, Math. Methods Oper. Res. 43, 121-139.
• R. Cavazos-Cadena and R. Montes-de-Oca (1999), Optimal stationarypolicies in controlled Markov chains with theexpected total-reward criterion, Research Report No. 1.01.010.99, Univ. Autónoma Metropolitana, Campus Iztapalapa, México, D.F.
• P. C. Fishburn (1970), Utility Theory for Decision Making, Wiley, New York.
• W. H. Fleming and D. Hernández-Hernández (1997), Risk-sensitive control of finite machines on an infinite horizon I, SIAM J. Control Optim. 35, 1790-1810.
• O. Hernández-Lerma (1989), Adaptive Markov Control Processes, Springer, New York.
• K. Hinderer (1970), Foundations of Non-Stationary Dynamic Programming with Discrete Time Parameter, Lecture Notes in Oper. Res. 33, Springer, New York.
• R. A. Howard and J. E. Matheson (1972), Risk-sensitive Markov decisionprocesses, Management Sci. 18, 356-369.
• M. Loève (1977), Probability Theory I, 4th ed., Springer, New York.
• J. W. Pratt (1964), Risk aversion in the small and in the large, Econometrica 32, 122-136.
• M. L. Puterman (1994), Markov Decision Processes, Wiley, New York.
• S. M. Ross (1970), Applied Probability Models with Optimization Applications, Holden-Day, San Francisco.
• R. Strauch (1966), Negative dynamic programming, Ann.Math. Statist. 37, 871-890.