Nevena Lazic, Dong Yin, Mehrdad Farajtabar, Nir Levine, Dilan Görür, Chris Harris, Dale Schuurmans. A Maximum-Entropy Approach to Off-Policy Evaluation in Average-Reward MDPs. 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{LazicYFLGHS20,
title = {A Maximum-Entropy Approach to Off-Policy Evaluation in Average-Reward MDPs},
author = {Nevena Lazic and Dong Yin and Mehrdad Farajtabar and Nir Levine and Dilan Görür and Chris Harris and Dale Schuurmans},
year = {2020},
url = {https://proceedings.neurips.cc/paper/2020/hash/9308b0d6e5898366a4a986bc33f3d3e7-Abstract.html},
researchr = {https://researchr.org/publication/LazicYFLGHS20},
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},
}