Counterfactual Reward Modification for Streaming Recommendation with Delayed Feedback.

@inproceedings{zhang-2021-counterfactual, author = {Xiao Zhang and Haonan Jia and Hanjing Su and Wenhan Wang and Jun Xu and Ji-Rong Wen}, editor = {Fernando Diaz and Chirag Shah and Torsten Suel and Pablo Castells and Rosie Jones and Tetsuya Sakai}, title = {{Counterfactual Reward Modification for Streaming Recommendation with Delayed Feedback}}, booktitle = {{SIGIR '21: The 44th International ACM SIGIR Conference on Research and Development in Information Retrieval, Virtual Event, Canada, July 11-15, 2021}}, pages = {41--50}, publisher = {ACM}, year = {2021}, url = {https://doi.org/10.1145/3404835.3462892}, doi = {https://doi.org/10.1145/3404835.3462892} }