%0 Journal Article %1 journals/corr/abs-2004-14507 %A Zhu, Qingfu %A Zhang, Weinan %A Liu, Ting %A Wang, William Yang %D 2020 %J CoRR %K dblp %T Counterfactual Off-Policy Training for Neural Response Generation. %U http://dblp.uni-trier.de/db/journals/corr/corr2004.html#abs-2004-14507 %V abs/2004.14507

@article{journals/corr/abs-2004-14507, added-at = {2020-05-03T00:00:00.000+0200}, author = {Zhu, Qingfu and Zhang, Weinan and Liu, Ting and Wang, William Yang}, biburl = {https://www.bibsonomy.org/bibtex/269a5c9ce692fc4f7e8352b6abfad66a0/dblp}, ee = {https://arxiv.org/abs/2004.14507}, interhash = {ddf6768e817e0e99b756d8de170632d9}, intrahash = {69a5c9ce692fc4f7e8352b6abfad66a0}, journal = {CoRR}, keywords = {dblp}, timestamp = {2020-05-05T11:43:11.000+0200}, title = {Counterfactual Off-Policy Training for Neural Response Generation.}, url = {http://dblp.uni-trier.de/db/journals/corr/corr2004.html#abs-2004-14507}, volume = {abs/2004.14507}, year = 2020 }