%0 Journal Article %1 journals/corr/abs-2310-13639 %A Hejna, Joey %A Rafailov, Rafael %A Sikchi, Harshit %A Finn, Chelsea %A Niekum, Scott %A Knox, W. Bradley %A Sadigh, Dorsa %D 2023 %J CoRR %K dblp %T Contrastive Preference Learning: Learning from Human Feedback without RL. %U http://dblp.uni-trier.de/db/journals/corr/corr2310.html#abs-2310-13639 %V abs/2310.13639

@article{journals/corr/abs-2310-13639, added-at = {2023-10-27T00:00:00.000+0200}, author = {Hejna, Joey and Rafailov, Rafael and Sikchi, Harshit and Finn, Chelsea and Niekum, Scott and Knox, W. Bradley and Sadigh, Dorsa}, biburl = {https://www.bibsonomy.org/bibtex/2781c8e6b5e8b6efe582dab0ebc6bea78/dblp}, ee = {https://doi.org/10.48550/arXiv.2310.13639}, interhash = {95841e1a8d03a30cb489a1ff89bfc1a8}, intrahash = {781c8e6b5e8b6efe582dab0ebc6bea78}, journal = {CoRR}, keywords = {dblp}, timestamp = {2024-04-09T00:24:22.000+0200}, title = {Contrastive Preference Learning: Learning from Human Feedback without RL.}, url = {http://dblp.uni-trier.de/db/journals/corr/corr2310.html#abs-2310-13639}, volume = {abs/2310.13639}, year = 2023 }