Article ID: | iaor20084677 |
Country: | United States |
Volume: | 2006 |
Issue: | 81593 |
Start Page Number: | 1 |
End Page Number: | 8 |
Publication Date: | Jan 2006 |
Journal: | Journal of Applied Mathematics and Stochastic Analysis |
Authors: | Guo Xianping, Zhu Quanxin |
Keywords: | programming: markov decision, stochastic processes, control |
This paper deals with discrete-time Markov decision processes with Borel state and action spaces. The criterion to be minimized is the average expected costs, and the costs may have neither upper nor lower bounds. In our former paper (to appear in