| Authored By: | Lawrence K. Saul and Satinder P. Singh |
| Paper Title: | Learning curve bounds for a Markov decision process with undiscounted rewards |
| Book/Journal Title: | Proc. 9th Annu. Conf. on Comput. Learning Theory |
| Publisher: | ACM Press, New York, NY |
| Publication Date: | 1996 |
| Pages: | 147-156 |