Sequential Search with Off-Policy Reinforcement Learning.

@inproceedings{miao-2021-sequential, author = {Dadong Miao and Yanan Wang and Guoyu Tang and Lin Liu and Sulong Xu and Bo Long and Yun Xiao and Lingfei Wu and Yunjiang Jiang}, editor = {Gianluca Demartini and Guido Zuccon and J. Shane Culpepper and Zi Huang and Hanghang Tong}, title = {{Sequential Search with Off-Policy Reinforcement Learning}}, booktitle = {{CIKM '21: The 30th ACM International Conference on Information and Knowledge Management, Virtual Event, Queensland, Australia, November 1 - 5, 2021}}, pages = {4006--4015}, publisher = {ACM}, year = {2021}, url = {https://doi.org/10.1145/3459637.3481954}, doi = {https://doi.org/10.1145/3459637.3481954} }