Discounted Approximations for Risk-Sensitive Average Criteria in Markov Decision Chains with Finite State Space

References

• Arapostathis A., Borkar V. K., Fernández-Gaucherand E., Gosh M. K., Marcus S. I. Discrete-time controlled Markov processes with average cost criteria: A survey. SIAM J. Control Optim. (1993) 31:282–334Crossref, Google Scholar
• Bather J. Optimal decision procedures for finite Markov chains. Part I: Examples. Adv. Appl. Probab. (1973) 5:328–339Crossref, Google Scholar
• Borkar V. S., Meyn S. P. Risk-sensitive optimal control for Markov decision process with monotone cost. Math. Oper. Res. (2002) 27:192–209Link, Google Scholar
• Cavazos-Cadena R. Solution to the risk-sensitive average cost optimality equation in a class of Markov decision processes with finite state space. Math. Methods Oper. Res. (2003) 57:263–285Crossref, Google Scholar
• Cavazos-Cadena R., Fernández-Gaucherand E. Controlled Markov chains with risk-sensitive criteria: Average cost, optimality equations and optimal solutions. Math. Methods Oper. Res. (1999) 43:121–139Google Scholar
• Cavazos-Cadena R., Hernández-Hernández D. Solution to the risk sensitive average optimality equation in communicating Markov decision chains with finite state space: An alternative approach. Math. Methods Oper. Res. (2002) 56:473–479Crossref, Google Scholar
• Cavazos–Cadena R., Hernández-Hernández D. A characterization of the optimal risk-sensitive average cost in finite controlled Markov chains. Ann. Appl. Probab. (2005) 15:175–212Crossref, Google Scholar
• Cavazos-Cadena R., Hernández-Hernández D. A system of Poisson equations for a non-constant Varadhan functional on a finite state space. Appl. Math. Optim. (2006) 53:101–119Crossref, Google Scholar
• Cavazos-Cadena R., Hernández-Hernández D. Contractive approximations for the Varadhan's functional on a finite Markov chain. Theory Probab. Appl. (2008) 52:315–323Crossref, Google Scholar
• Chitashvili R. Y. A controlled Markov chain with an arbitrary set of decisions. Theory Probab. Appl. (1975) 20:839–846Crossref, Google Scholar
• Denardo E. V., Rothblum U. G. A turnpike theorem for risk-sensitive Markov decision processes with stopping. SIAM J. Control Optim. (2006) 45:414–431Crossref, Google Scholar
• Di Masi G. B., Stettner L. Infinite horizon risk sensitive control of discrete time Markov processes with small risk. Systems Control Lett. (2000) 40:305–321Crossref, Google Scholar
• Di Masi G. B., Stettner L. Infinite horizon risk sensitive control of discrete time Markov processes under minorization property. SIAM J. Control Optim. (2007) 46:231–252Crossref, Google Scholar
• Feinberg E. A. On controlled finite state Markov processes with compact control sets. Theory Probab. Appl. (1975) 20:856–861Crossref, Google Scholar
• Feinberg E. A. The existence of a stationary ε-optimal policy for a finite Markov chain. Theory Probab. Appl. (1978) 23:297–313Crossref, Google Scholar
• Fleming W. H., McEneany W. M. Risk-sensitive control on an infinite horizon. SIAM J. Control Optim. (1995) 33:1881–1915Crossref, Google Scholar
• Hernández-Hernández D., Marcus S. I. Risk-sensitive control of Markov processes in countable state space. Systems Control Lett. (1996) 29:147–155Crossref, Google Scholar
• Hernández-Hernández D., Marcus S. I. Existence of risk-sensitive optimal stationary policies for controlled Markov processes. Appl. Math. Optim. (1999) 40:273–285Crossref, Google Scholar
• Hernández-Lerma O.Adaptive Markov Control Processes (1988) (Springer, New York) Google Scholar
• Howard A. R., Matheson J. E. Risk-sensitive Markov decision processes. Management Sci. (1972) 18:356–369Link, Google Scholar
• Jacobson D. H. Optimal stochastic linear systems with exponential performance criteria and their relation to stochastic differential games. IEEE Trans. Automatic Control (1973) 18:124–131Crossref, Google Scholar
• Jaquette S. C. Markov decision processes with a new optimality criterion: Discrete time. Ann. Statist. (1973) 1:496–505Crossref, Google Scholar
• Jaquette S. C. A utility criterion for Markov decision processes. Management Sci. (1976) 23:43–49Link, Google Scholar
• Jaśkiewicz A. Average optimality for risk sensitive control with general state space. Ann. Appl. Probab. (2007) 17:654–675Crossref, Google Scholar
• Montes-de-Oca R., Hernández-Lerma O. Conditions for average optimality in Markov control processes with unbounded costs and controls. J. Math. Systems Estim. Control (1994) 4:1–19Google Scholar
• Puterman M. L.Markov Decision Processes (1994) (Wiley, New York) Crossref, Google Scholar
• Sennott L. I. A new condition for the existence of optimum stationary policies in average cost Markov decision processes. Oper. Res. Lett. (1986) 5:17–23Crossref, Google Scholar
• Sennott L. I. Another set of conditions for average optimality in Markov control processes. Systems Control Lett. (1995) 24:147–151Crossref, Google Scholar
• Sladký K. Growth rates and average optimality in risk-sensitive Markov decision chains. Kybernetika (2008) 44:205–226Google Scholar
• Sladký K., Montes-de-Oca R., Kalcsics J., Nickel S. Risk-sensitive average optimality in Markov decision chains. Operations Ressearch Proceedings (2007) (Springer, New York) 69–74Google Scholar