| Authored By: | John N. Tsitsiklis and Benjamin Van Roy |
| Paper Title: | On Average Versus Discounted Reward Temporal-Difference Learning |
| In: | Machine Learning |
| Number 2-3 Vol. 49 | |
| Publisher: | Kluwer Academic Publishers, Boston |
| Publication Date: | 2002 |
| Pages: | 179-191 |