Remarks on maximal meanstandard devition ratio in undiscounted mdps

Abstract

In the steady state of an undiscounted Markov decision process, we consider the problem to find an optimal stationary probability distribution that maximizes the mean standard deviation ratio among all the stationary probability distributions. The problem injects considerations in MDPs from the relative point of view

Keywords:

• Markov decision process
• Parametric analysis
• Mean-variance

^*This research was supported by the National Science Council of the Republic of China (NSC82-0415-E011-073)

^*This research was supported by the National Science Council of the Republic of China (NSC82-0415-E011-073)

Notes

^*This research was supported by the National Science Council of the Republic of China (NSC82-0415-E011-073)