Human-centric dialog training via offline reinforcement learning

Detalhes bibliográficos
Principais autores:	Jaques, Natasha, Shen, Judy Hanwen, Ghandeharioun, Asma, Ferguson, Craig, Lapedriza, Agata, Jones, Noah, Gu, Shixiang, Picard, Rosalind W.
Outros Autores:	Program in Media Arts and Sciences (Massachusetts Institute of Technology)
Formato:	Artigo
Idioma:	English
Publicado em:	Association for Computational Linguistics (ACL) 2022
Acesso em linha:	https://hdl.handle.net/1721.1/146608

Internet

https://hdl.handle.net/1721.1/146608