Michael O. Duff
Q-Learning for Bandit Problems
ICML, 1995.
@inproceedings{ICML-1995-Duff, author = "Michael O. Duff", booktitle = "{Proceedings of the 12th International Conference on Machine Learning}", isbn = "1-55860-377-8", pages = "209--217", publisher = "{Morgan Kaufmann}", title = "{Q-Learning for Bandit Problems}", year = 1995, }