%0 Journal Article %1 journals/connection/QiuZY23 %A Qiu, Junyan %A Zhang, Haidong %A Yang, Yiping %D 2023 %J Connect. Sci. %K dblp %N 1 %T Reward estimation with scheduled knowledge distillation for dialogue policy learning. %U http://dblp.uni-trier.de/db/journals/connection/connection35.html#QiuZY23 %V 35

@article{journals/connection/QiuZY23, added-at = {2023-05-13T00:00:00.000+0200}, author = {Qiu, Junyan and Zhang, Haidong and Yang, Yiping}, biburl = {https://www.bibsonomy.org/bibtex/2b2ff75169fbe446af33f7921348c28db/dblp}, ee = {https://doi.org/10.1080/09540091.2023.2174078}, interhash = {1b869c525b041ff5f54cbd07fb4ed17b}, intrahash = {b2ff75169fbe446af33f7921348c28db}, journal = {Connect. Sci.}, keywords = {dblp}, month = {December}, number = 1, timestamp = {2024-04-08T21:31:31.000+0200}, title = {Reward estimation with scheduled knowledge distillation for dialogue policy learning.}, url = {http://dblp.uni-trier.de/db/journals/connection/connection35.html#QiuZY23}, volume = 35, year = 2023 }