@article{counterfactualoffpolicytrainingforneural, title = {Counterfactual Off-Policy Training for Neural Response Generation}, author = {Qingfu Zhu and Wei-Nan Zhang and Ting Liu and William Yang Wang}, year = {2020}, eprint = {2004.14507}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2004.14507v2}, }