Abstract
We develop the theory for Markov and semi-Markov control using dynamic programming and reinforcement learning in which a form of semi-variance which computes the variability of rewards below a pre-specified target is penalized. The objective is to optimize a function of the rewards and risk where risk is penalized. Penalizing variance, which is popular in the literature, has some drawbacks that can be avoided with semi-variance.
Similar content being viewed by others
References
J. Abounadi, D. Bertsekas, and V. Borkar, “Learning algorithms for Markov decision processes with average cost,” SIAM Journal of Control and Optimization, vol. 40, pp. 681–698, 2001.
E. Altman, Constrained Markov Decision Processes, CRC Press, Boca Raton, 1998.
J. Baxter and P. Bartlett, “Infinite-horizon policygradient estimation,” Journal of Artificial Intelligence, vol. 15, pp. 319–350, 2001.
D. P. Bertsekas and J. Tsitsiklis, Neuro-Dynamic Programming, Athena, Belmont, 1996.
D. P. Bertsekas, Dynamic Programming and Optimal Control, 2nd edition, Athena, Belmont, 2000.
T. Bielecki, D. Hernandez-Hernandez, and S. Pliska, “Risk-sensitive control of finite state Markov chains in discrete time,” Math. Methods of Opns. Research, vol. 50, pp. 167–188, 1999.
K. Boda and J. Filar, “Time consistent dynamic risk measures,” Mathematical Methods of Operations Research, vol. 63, pp. 169–186, 2005.
V. Borkar and S. Meyn, “Risk-sensitive optimal control for Markov decision processes with monotone cost,” Mathematics of Operations Research, vol. 27, pp. 192–209, 2002.
V. S. Borkar, “Stochastic approximation with two-time scales,” Systems and Control Letters, vol. 29, pp. 291–294, 1997.
V. S. Borkar, “Asynchronous stochastic approximation,” SIAM Journal of Control and Optimization, vol. 36, no. 3, pp. 840–851, 1998.
V. S. Borkar and S. P. Meyn, “The ODE method for convergence of stochastic approximation and reinforcement learning,” SIAM Journal of Control and Optimization, vol. 38, no. 2, pp. 447–469, 2000.
V. S. Borkar and K. Soumyanath, “A new analog parallel scheme for fixed point computation, part I: Theory,” IEEE Trans. on Circuits and Systems I: Theory and Applications, vol. 44, pp. 351–355, 1997.
M. Bouakiz and Y. Kebir, “Target-level criterion in Markov decision processes,” Journal of Optimization Theory and Applications, vol. 86, pp. 1–15, 1995.
S. J. Bradtke and M. Duff, “Reinforcement learning methods for continuous-time MDPs,” In Advances in Neural Information Processing Systems 7. MIT Press, Cambridge, MA, USA, 1995.
F. Brauer and J. Nohel, The Qualitative Theory of Ordinary Differential Equations: An Introduction, Dover Publishers, New York, 1989.
X.-R. Cao, “From perturbation analysis to Markov decision processes and reinforcement learning,” Discrete-Event Dynamic Systems: Theory and Applications, vol. 13, pp. 9–39, 2003.
X.-R. Cao, “Semi-Markov decision problems and performance sensitivity analysis,” IEEE Trans. on Automatic Control, vol. 48, no. 5, pp. 758–768, 2003.
R. Cavazos-Cadena, “Solution to risk-sensitive average cost optimality equation in a class of MDPs with finite state space,” Math. Methods of Opns. Research, vol. 57, pp. 253–285, 2003.
R. Cavazos-Cadena and E. Fernandez-Gaucherand, “Controlled Markov chains with risk-sensitive criteria,” Mathematical Models of Operations Research, vol. 43, pp. 121–139, 1999.
R.-R. Chen and S. Meyn, “Value iteration and optimization of multiclass queueing networks,” Queueing Systems, vol. 32, pp. 65–97, 1999.
K. Chung and M. Sobel, “Discounted MDPs: distribution functions and exponential utility maximization,” SIAM Journal of Control and Optimization, vol. 25, pp. 49–62, 1987.
G. Di Masi and L. Stettner, “Risk-sensitive control of discrete-time Markov processes with infinite horizon,” SIAM Journal of Control and Optimization, vol. 38, no. 1, pp. 61–78, 1999.
J. Estrada, “Mean-semivariance behavior: Downside risk and capital asset pricing,” International Review of Economics and Finance, vol. 16, pp. 169–185, 2007.
J. Filar, L. Kallenberg, and H. Lee, “Variancepenalized Markov decision processes,” Mathematics of Operations Research, vol. 14, no 1, pp. 147–161, 1989.
J. Filar, D. Krass, and K. Ross, “Percentile perfor mance criteria for limiting average Markov decision processes,” IEEE Trans. on Automatic Control, vol. 40, pp. 2–10, 1995.
W. Fleming and D. Hernandez-Hernandez, “Risksensitive control of finite state machines on an infinte horizon,” SIAM Journal of Control and Optimization, vol. 35, pp. 1790–1810, 1997.
A. Gosavi, “Reinforcement learning for long-run average cost,” European Journal of Operational Research, vol. 155, pp. 654–674, 2004.
A. Gosavi, “A risk-sensitive approach to total productive maintenance,” Automatica, vol. 42, pp. 1321–1330, 2006.
A. Gosavi, S. L. Murray, V. M. Tirumalasetty, and S. Shewade, “A budget-sensitive approach to scheduling maintenance in a total productive maintenance (TPM),” Engineering Management Journal, vol. 23, no. 3, pp. 46–56, 2011.
D. Hernandez-Hernandez and S. Marcus, “Risksensitive control of Markov processes in countable state space,” Systems and Control Letters, vol. 29, pp. 147–155, 1996.
R. Howard and J. Matheson, “Risk-sensitive MDPs,” Management Science, vol. 18, no. 7, pp. 356–369, 1972.
G. Hübner, “Improved procedures for eliminating sub-optimal actions in Markov programming by the use of contraction properties,” Transactions of 7th Prague Conference on Information Theory, Statistical Decision Functions, Random Processes, pp. 257–263, Dordrecht, 1978.
Q. Jiang, H.-S. Xi, and B.-Q. Yin, “Dynamic file grouping for load balancing in streaming media clustered server systems,” International Journal of Control, Automation, and Systems, vol. 7, no. 4, pp. 630–637, 2009.
W. Y. Kwon, H. Suh, and S. Lee, “SSPQL: stochastic shortest path-based Q-learning,” International Journal of Control, Automation, and Systems, vol. 9, no. 2, pp. 328–338, 2011.
A. E. B. Lim and X. Y. Zhou, “Risk-sensitive control with HARA utility,” IEEE Trans. on Automatic Control, vol. 46, no. 4, pp. 563–578, 2001.
R. Porter, “Semivariance and stochastic dominance,” American Economic Review, vol. 64, pp. 200–204, 1974.
M. L. Puterman, Markov Decision Processes, Wiley Interscience, New York, 1994.
S. Ross, Applied Probability Models with Optimization Applications, Dover, New York, 1992.
E. Seneta, Non-Negative Matrices and Markov Chains, Springer-Verlag, NY, 1981.
S. Singh, V. Tadic, and A. Doucet, “A policygradient method for semi-Markov decision processes with application to call admission control,” European Journal of Operational Research, vol. 178, no. 3, pp. 808–818, 2007.
M. Sobel, “The variance of discounted Markov decision processes,” Journal of Applied Probability, vol. 19, pp. 794–802, 1982.
H. C. Tijms, A First Course in Stochastic Models, 2nd edition, Wiley, 2003.
C. G. Turvey and G. Nayak, “The semi-varianceminimizing hedge ratios,” Journal of Agricultural and Resource Economics, vol. 28, no. 1, pp. 100–115, 2003.
D. White, “Minimizing a threshold probability in discounted Markov decision processes,” Journal of Mathematical Analysis and Applications, vol. 173, pp. 634–646, 1993.
C. Wu and Y. Lin, “Minimizing risk models in Markov decision processes with policies depending on target values,” Journal of Mathematical Analysis and Applications, vol. 231, pp. 47–67, 1999.
Author information
Authors and Affiliations
Corresponding author
Additional information
Recommended by Editor Young Il Lee. The author would like to acknowledge support from NSF grant ECCS: 0841055 that partially funded this research.
Abhijit Gosavi received his B.E in Mechanical Engineering from Jadavpur University in 1992, an M.Tech in Mechanical Engineering from the Indian Institute of Technology, Madras in 1995, and a Ph.D. in Industrial Engineering from the University of South Florida. His research interests include Markov decision processes, simulation, and applied operations research. He joined the Missouri University of Science and Technology in 2008 as an Assistant Professor.
Rights and permissions
About this article
Cite this article
Gosavi, A. Target-sensitive control of Markov and semi-Markov processes. Int. J. Control Autom. Syst. 9, 941–951 (2011). https://doi.org/10.1007/s12555-011-0515-6
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s12555-011-0515-6