| Article ID: | iaor19942344 |
| Country: | Germany |
| Volume: | 26 |
| Start Page Number: | 385 |
| End Page Number: | 392 |
| Publication Date: | Mar 1992 |
| Journal: | Optimization |
| Authors: | Chung K.-J. |
In the steady state of an undiscounted Markov decision process, the paper considers 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.