Reinforcement Learning to Rank with Pairwise Policy Gradient.

@inproceedings{xu-2020-reinforcement, author = {Jun Xu and Zeng Wei and Long Xia and Yanyan Lan and Dawei Yin and Xueqi Cheng and Ji-Rong Wen}, editor = {Jimmy Huang and Yi Chang and Xueqi Cheng and Jaap Kamps and Vanessa Murdock and Ji-Rong Wen and Yiqun Liu}, title = {{Reinforcement Learning to Rank with Pairwise Policy Gradient}}, booktitle = {{Proceedings of the 43rd International ACM SIGIR conference on research and development in Information Retrieval, SIGIR 2020, Virtual Event, China, July 25-30, 2020}}, pages = {509--518}, publisher = {ACM}, year = {2020}, url = {https://doi.org/10.1145/3397271.3401148}, doi = {https://doi.org/10.1145/3397271.3401148} }