BibTeX record journals/corr/abs-1907-00456

download as .bib file

@article{DBLP:journals/corr/abs-1907-00456,
  author    = {Natasha Jaques and
               Asma Ghandeharioun and
               Judy Hanwen Shen and
               Craig Ferguson and
               {\`{A}}gata Lapedriza and
               Noah Jones and
               Shixiang Gu and
               Rosalind W. Picard},
  title     = {Way Off-Policy Batch Deep Reinforcement Learning of Implicit Human
               Preferences in Dialog},
  journal   = {CoRR},
  volume    = {abs/1907.00456},
  year      = {2019},
  url       = {http://arxiv.org/abs/1907.00456},
  archivePrefix = {arXiv},
  eprint    = {1907.00456},
  timestamp = {Mon, 08 Jul 2019 14:12:33 +0200},
  biburl    = {https://dblp.org/rec/bib/journals/corr/abs-1907-00456},
  bibsource = {dblp computer science bibliography, https://dblp.org}
}
a service of Schloss Dagstuhl - Leibniz Center for Informatics