Loading...
Please wait, while we are loading the content...
Similar Documents
Nonatomic total rewards Markov decision processes with multiple criteria
Content Provider | Semantic Scholar |
---|---|
Author | Feinberg, Eugene A. Piunovskiy, Aleksey B. |
Copyright Year | 2002 |
Abstract | We consider a Markov decision process with an uncountable state space for which the vector performance functional has the form of expected total rewards. Under the single condition that initial distribution and transition probabilities are nonatomic, we prove that the performance space coincides with that generated by nonrandomized Markov policies. We also provide conditions for the existence of optimal policies when the goal is to maximize one component of the performance vector subject to inequality constraints on other components. We illustrate our results with examples of production and financial problems. |
Starting Page | 93 |
Ending Page | 111 |
Page Count | 19 |
File Format | PDF HTM / HTML |
DOI | 10.1016/S0022-247X(02)00213-5 |
Volume Number | 273 |
Alternate Webpage(s) | http://www.ams.sunysb.edu/~feinberg/public/JMAA2003.pdf |
Alternate Webpage(s) | https://doi.org/10.1016/S0022-247X%2802%2900213-5 |
Language | English |
Access Restriction | Open |
Content Type | Text |
Resource Type | Article |