Mengjiao Yang, Ofir Nachum, Bo Dai, Lihong Li 0001, Dale Schuurmans. Off-Policy Evaluation via the Regularized Lagrangian. In Hugo Larochelle, Marc'Aurelio Ranzato, Raia Hadsell, Maria-Florina Balcan, Hsuan-Tien Lin, editors, Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, NeurIPS 2020, December 6-12, 2020, virtual. 2020. [doi]
@inproceedings{YangND0S20,
title = {Off-Policy Evaluation via the Regularized Lagrangian},
author = {Mengjiao Yang and Ofir Nachum and Bo Dai and Lihong Li 0001 and Dale Schuurmans},
year = {2020},
url = {https://proceedings.neurips.cc/paper/2020/hash/488e4104520c6aab692863cc1dba45af-Abstract.html},
researchr = {https://researchr.org/publication/YangND0S20},
cites = {0},
citedby = {0},
booktitle = {Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, NeurIPS 2020, December 6-12, 2020, virtual},
editor = {Hugo Larochelle and Marc'Aurelio Ranzato and Raia Hadsell and Maria-Florina Balcan and Hsuan-Tien Lin},
}