| Article ID: | iaor19982370 |
| Country: | United States |
| Volume: | 6 |
| Issue: | 2 |
| Start Page Number: | 188 |
| End Page Number: | 192 |
| Publication Date: | Mar 1994 |
| Journal: | ORSA Journal On Computing |
| Authors: | Melekopoglou Mary, Condon Anne |
| Keywords: | optimization, control processes, programming: dynamic |
We consider the complexity of the policy improvement algorithm for Markov decision processes. We show that four variants of the algorithm require exponential time in the worst case.