Chengqian Gao, Ke Xu, Kuangqi Zhou, Lanqing Li, Xueqian Wang, Bo Yuan, Peilin Zhao. Value Penalized Q-Learning for Recommender Systems. In Enrique Amigó, Pablo Castells, Julio Gonzalo, Ben Carterette, J. Shane Culpepper, Gabriella Kazai, editors, SIGIR '22: The 45th International ACM SIGIR Conference on Research and Development in Information Retrieval, Madrid, Spain, July 11 - 15, 2022. pages 2008-2012, ACM, 2022. [doi]
@inproceedings{GaoXZLWYZ22, title = {Value Penalized Q-Learning for Recommender Systems}, author = {Chengqian Gao and Ke Xu and Kuangqi Zhou and Lanqing Li and Xueqian Wang and Bo Yuan and Peilin Zhao}, year = {2022}, doi = {10.1145/3477495.3531796}, url = {https://doi.org/10.1145/3477495.3531796}, researchr = {https://researchr.org/publication/GaoXZLWYZ22}, cites = {0}, citedby = {0}, pages = {2008-2012}, booktitle = {SIGIR '22: The 45th International ACM SIGIR Conference on Research and Development in Information Retrieval, Madrid, Spain, July 11 - 15, 2022}, editor = {Enrique Amigó and Pablo Castells and Julio Gonzalo and Ben Carterette and J. Shane Culpepper and Gabriella Kazai}, publisher = {ACM}, isbn = {978-1-4503-8732-3}, }