%0 Journal Article %1 journals/corr/abs-2403-07708 %A Shen, Wei %A Zhang, Xiaoying %A Yao, Yuanshun %A Zheng, Rui %A Guo, Hongyi %A Liu, Yang %D 2024 %J CoRR %K dblp %T Improving Reinforcement Learning from Human Feedback Using Contrastive Rewards. %U http://dblp.uni-trier.de/db/journals/corr/corr2403.html#abs-2403-07708 %V abs/2403.07708

@article{journals/corr/abs-2403-07708, added-at = {2024-04-04T00:00:00.000+0200}, author = {Shen, Wei and Zhang, Xiaoying and Yao, Yuanshun and Zheng, Rui and Guo, Hongyi and Liu, Yang}, biburl = {https://www.bibsonomy.org/bibtex/242577de5f71b7add67c6a7d9ffbbea4e/dblp}, ee = {https://doi.org/10.48550/arXiv.2403.07708}, interhash = {22a1bec76923f36d6d595f4d8dfccfed}, intrahash = {42577de5f71b7add67c6a7d9ffbbea4e}, journal = {CoRR}, keywords = {dblp}, timestamp = {2024-04-09T00:18:08.000+0200}, title = {Improving Reinforcement Learning from Human Feedback Using Contrastive Rewards.}, url = {http://dblp.uni-trier.de/db/journals/corr/corr2403.html#abs-2403-07708}, volume = {abs/2403.07708}, year = 2024 }