Sherief Abdallah, Michael Kaisers. Addressing the policy-bias of q-learning by repeating updates. In Maria L. Gini, Onn Shehory, Takayuki Ito, Catholijn M. Jonker, editors, International conference on Autonomous Agents and Multi-Agent Systems, AAMAS '13, Saint Paul, MN, USA, May 6-10, 2013. pages 1045-1052, IFAAMAS, 2013. [doi]
@inproceedings{AbdallahK13,
title = {Addressing the policy-bias of q-learning by repeating updates},
author = {Sherief Abdallah and Michael Kaisers},
year = {2013},
url = {http://dl.acm.org/citation.cfm?id=2485085},
researchr = {https://researchr.org/publication/AbdallahK13},
cites = {0},
citedby = {0},
pages = {1045-1052},
booktitle = {International conference on Autonomous Agents and Multi-Agent Systems, AAMAS '13, Saint Paul, MN, USA, May 6-10, 2013},
editor = {Maria L. Gini and Onn Shehory and Takayuki Ito and Catholijn M. Jonker},
publisher = {IFAAMAS},
isbn = {978-1-4503-1993-5},
}