Risk-Sensitive Optimal Control for Markov Decision Processes with Monotone Cost

References

• Balaji S., Meyn S. P. Multiplicative ergodic theorems and large deviations for an irreducible Markov chain. Stochastic Processes Their Appl. (2000) 90(1):123–144Crossref, Google Scholar
• Bellman R.Dynamic Programming (1957) (Princeton University Press, Princeton, NJ) Google Scholar
• Cavazos-Cadena R., Fernandez-Gaucherand E. Controlled Markov chains with risk-sensitive criteria: Average cost, optimality equations, and optimal solutions. Math. Methods Oper. Res. (1999) 49:299–324Google Scholar
• Chen R-R., Meyn S. P. Value iteration and optimization of multiclass queueing networks. Queueing Systems (1999) 32:65–97Crossref, Google Scholar
• Chow Y., Teicher H.Probability Theory: Independence, Interchangeability, Martingales (1988) (Springer-Verlag, New York) Crossref, Google Scholar
• D̃i Masi G. B., Stettner L. Risk sensitive control of discrete time partially observed Markov processes with infinite horizon. SIAM J. Control Optim. (1999) 38(1):61–78Crossref, Google Scholar
• Fleming W. H., Hernández-Hernández D. Risk sensitive control of finite state machines on an infinite horizon i. SIAM J. Control Optim. (1997) 45:1790–1810Crossref, Google Scholar
• Fleming W. H., McEneaney W. M., Lawrence K. S. Risk sensitive optimal control and differential games. Stochastic Theory and Adaptive Control (1991) (Springer, Berlin, Germany) 185–197Google Scholar
• Glynn P. W., Meyn S. P. A Lyapunov bound for solutions of Poisson's equation. Ann. Probab. (1996) 24:916–931Crossref, Google Scholar
• Hernández-Hernández D., Marcus S. I. Risk sensitive control of Markov processes in countable state space. Systems Control Lett. (1998) 29:147–155Correction in Systems and Control Lett. 34(1–2), 1998, 105–106Crossref, Google Scholar
• Howard R. A., Matheson J. E. Risk-sensitive Markov decision processes. Management Sci. (1972) 8:356–369Link, Google Scholar
• Jacobson D. H. Optimal stochastic linear systems with exponential performance criteria and their relation to deterministic differential games. IEEE Trans. Automatic Control (1973) AC-18:124–131Crossref, Google Scholar
• James M. R., Baras J., Elliott R. J. Risk-sensitive control and dynamic games for partially observed discrete-time nonlinear systems. IEEE Trans. Automatic. Control (1994) AC-39(4):780–792Crossref, Google Scholar
• Kontoyiannis I., Meyn S. P. Precise limit theorems and multiplicative ergodicity for Markov processes. (2001) . Working paper, INFORMS Applied Probability Conference, New YorkGoogle Scholar
• Meyn S. P. The policy improvement algorithm for Markov decision processes with general state space. IEEE Trans. Automatic Control (1997) AC-42:1663–1680Crossref, Google Scholar
• Meyn S. P. Algorithms for optimization and stabilization of controlled Markov chains. SADHANA (Proceedings of the Indian Academy of Sciences Engineering Sciences) (1999) 24October:339–368Google Scholar
• Meyn S. P., Tweedie R. L.Markov Chains and Stochastic Stability (1993) (Springer-Verlag, London) Crossref, Google Scholar
• Nummelin E.General Irreducible Markov Chains and Nonnegative Operators (1984) (Cambridge University Press, Cambridge, U.K.) Crossref, Google Scholar
• Rothblum U. G. Multiplicative Markov decision chains. Math. Oper. Res. (1984) 9:6–24Link, Google Scholar
• Seneta E.Non-Negative Matrices and Markov Chains (1981) 2nd ed.(Springer, New York) Crossref, Google Scholar
• Whittle P.Risk-Sensitive Optimal Control (1990) (John Wiley and Sons, Chichester, U.K.) Google Scholar
• Whittle P.Optimisation: Basics and Beyond (1996) (John Wiley and Sons, Chichester, U.K.) Google Scholar