%0 Journal Article %1 journals/corr/abs-1712-02838 %A Zhou, Li %A Small, Kevin %A Rokhlenko, Oleg %A Elkan, Charles %D 2017 %J CoRR %K dblp %T End-to-End Offline Goal-Oriented Dialog Policy Learning via Policy Gradient. %U http://dblp.uni-trier.de/db/journals/corr/corr1712.html#abs-1712-02838 %V abs/1712.02838

@article{journals/corr/abs-1712-02838, added-at = {2020-09-06T00:00:00.000+0200}, author = {Zhou, Li and Small, Kevin and Rokhlenko, Oleg and Elkan, Charles}, biburl = {https://www.bibsonomy.org/bibtex/207fb3da7a204587d10a83748eefcf137/dblp}, ee = {http://arxiv.org/abs/1712.02838}, interhash = {e635da2e7e7cc70cb345690fc069af8a}, intrahash = {07fb3da7a204587d10a83748eefcf137}, journal = {CoRR}, keywords = {dblp}, timestamp = {2020-09-09T12:45:03.000+0200}, title = {End-to-End Offline Goal-Oriented Dialog Policy Learning via Policy Gradient.}, url = {http://dblp.uni-trier.de/db/journals/corr/corr1712.html#abs-1712-02838}, volume = {abs/1712.02838}, year = 2017 }