Пожалуйста, войдите в систему, чтобы принять участие в дискуссии (добавить собственные рецензию, или комментарий)
Цитировать эту публикацию
%0 Journal Article
%1 journals/corr/abs-2312-00886
%A Munos, Rémi
%A Valko, Michal
%A Calandriello, Daniele
%A Azar, Mohammad Gheshlaghi
%A Rowland, Mark
%A Guo, Zhaohan Daniel
%A Tang, Yunhao
%A Geist, Matthieu
%A Mesnard, Thomas
%A Michi, Andrea
%A Selvi, Marco
%A Girgin, Sertan
%A Momchev, Nikola
%A Bachem, Olivier
%A Mankowitz, Daniel J.
%A Precup, Doina
%A Piot, Bilal
%D 2023
%J CoRR
%K dblp
%T Nash Learning from Human Feedback.
%U http://dblp.uni-trier.de/db/journals/corr/corr2312.html#abs-2312-00886
%V abs/2312.00886
@article{journals/corr/abs-2312-00886,
added-at = {2024-01-02T00:00:00.000+0100},
author = {Munos, Rémi and Valko, Michal and Calandriello, Daniele and Azar, Mohammad Gheshlaghi and Rowland, Mark and Guo, Zhaohan Daniel and Tang, Yunhao and Geist, Matthieu and Mesnard, Thomas and Michi, Andrea and Selvi, Marco and Girgin, Sertan and Momchev, Nikola and Bachem, Olivier and Mankowitz, Daniel J. and Precup, Doina and Piot, Bilal},
biburl = {https://www.bibsonomy.org/bibtex/24bb4d74e7493da2d4d63142c8ff5eaeb/dblp},
ee = {https://doi.org/10.48550/arXiv.2312.00886},
interhash = {5dd7e4fc2a921ac0bbf96c3fc1a51ca8},
intrahash = {4bb4d74e7493da2d4d63142c8ff5eaeb},
journal = {CoRR},
keywords = {dblp},
timestamp = {2024-04-08T22:41:17.000+0200},
title = {Nash Learning from Human Feedback.},
url = {http://dblp.uni-trier.de/db/journals/corr/corr2312.html#abs-2312-00886},
volume = {abs/2312.00886},
year = 2023
}