Please log in to take part in the discussion (add own reviews or comments).
Cite this publication
More citation styles
- please select -
%0 Journal Article
%1 journals/corr/abs-2402-00782
%A Chan, Alex J.
%A Sun, Hao
%A Holt, Samuel
%A van der Schaar, Mihaela
%D 2024
%J CoRR
%K dblp
%T Dense Reward for Free in Reinforcement Learning from Human Feedback.
%U http://dblp.uni-trier.de/db/journals/corr/corr2402.html#abs-2402-00782
%V abs/2402.00782
@article{journals/corr/abs-2402-00782,
added-at = {2024-02-09T00:00:00.000+0100},
author = {Chan, Alex J. and Sun, Hao and Holt, Samuel and van der Schaar, Mihaela},
biburl = {https://www.bibsonomy.org/bibtex/2955b769695c86d30374e6cb9b7920a76/dblp},
ee = {https://doi.org/10.48550/arXiv.2402.00782},
interhash = {50af00185e3a4bb047beeec17b66aae7},
intrahash = {955b769695c86d30374e6cb9b7920a76},
journal = {CoRR},
keywords = {dblp},
timestamp = {2024-04-08T23:57:44.000+0200},
title = {Dense Reward for Free in Reinforcement Learning from Human Feedback.},
url = {http://dblp.uni-trier.de/db/journals/corr/corr2402.html#abs-2402-00782},
volume = {abs/2402.00782},
year = 2024
}