Haoqi Zhang, David C. Parkes, Yiling Chen. Policy teaching through reward function learning. In John Chuang, Lance Fortnow, Pearl Pu, editors, Proceedings 10th ACM Conference on Electronic Commerce (EC-2009), Stanford, California, USA, July 6--10, 2009. pages 295-304, ACM, 2009. [doi]
@inproceedings{ZhangPC09-0,
title = {Policy teaching through reward function learning},
author = {Haoqi Zhang and David C. Parkes and Yiling Chen},
year = {2009},
doi = {10.1145/1566374.1566417},
url = {http://doi.acm.org/10.1145/1566374.1566417},
tags = {C++, teaching},
researchr = {https://researchr.org/publication/ZhangPC09-0},
cites = {0},
citedby = {0},
pages = {295-304},
booktitle = {Proceedings 10th ACM Conference on Electronic Commerce (EC-2009), Stanford, California, USA, July 6--10, 2009},
editor = {John Chuang and Lance Fortnow and Pearl Pu},
publisher = {ACM},
isbn = {978-1-60558-458-4},
}