Value Penalized Q-Learning for Recommender Systems.

@inproceedings{gao-2022-value, author = {Chengqian Gao and Ke Xu and Kuangqi Zhou and Lanqing Li and Xueqian Wang and Bo Yuan and Peilin Zhao}, editor = {Enrique Amig\'{o} and Pablo Castells and Julio Gonzalo and Ben Carterette and J. Shane Culpepper and Gabriella Kazai}, title = {{Value Penalized Q-Learning for Recommender Systems}}, booktitle = {{SIGIR '22: The 45th International ACM SIGIR Conference on Research and Development in Information Retrieval, Madrid, Spain, July 11 - 15, 2022}}, pages = {2008--2012}, publisher = {ACM}, year = {2022}, url = {https://doi.org/10.1145/3477495.3531796}, doi = {https://doi.org/10.1145/3477495.3531796} }