Top-K Off-Policy Correction for a REINFORCE Recommender System.

@inproceedings{chen-2019-topk, author = {Minmin Chen and Alex Beutel and Paul Covington and Sagar Jain and Francois Belletti and Ed H. Chi}, editor = {J. Shane Culpepper and Alistair Moffat and Paul N. Bennett and Kristina Lerman}, title = {{Top-K Off-Policy Correction for a REINFORCE Recommender System}}, booktitle = {{Proceedings of the Twelfth ACM International Conference on Web Search and Data Mining, WSDM 2019, Melbourne, VIC, Australia, February 11-15, 2019}}, pages = {456--464}, publisher = {ACM}, year = {2019}, url = {https://doi.org/10.1145/3289600.3290999}, doi = {https://doi.org/10.1145/3289600.3290999} }