%0 Journal Article %1 journals/corr/abs-2312-14436 %A Chakraborty, Souradip %A Bhaskar, Amisha %A Singh, Anukriti %A Tokekar, Pratap %A Manocha, Dinesh %A Bedi, Amrit Singh %D 2023 %J CoRR %K dblp %T REBEL: A Regularization-Based Solution for Reward Overoptimization in Reinforcement Learning from Human Feedback. %U http://dblp.uni-trier.de/db/journals/corr/corr2312.html#abs-2312-14436 %V abs/2312.14436

@article{journals/corr/abs-2312-14436, added-at = {2024-01-17T00:00:00.000+0100}, author = {Chakraborty, Souradip and Bhaskar, Amisha and Singh, Anukriti and Tokekar, Pratap and Manocha, Dinesh and Bedi, Amrit Singh}, biburl = {https://www.bibsonomy.org/bibtex/20d335998a948b004885341718948fdab/dblp}, ee = {https://doi.org/10.48550/arXiv.2312.14436}, interhash = {d953919f20dce8770d082552af2681c4}, intrahash = {0d335998a948b004885341718948fdab}, journal = {CoRR}, keywords = {dblp}, timestamp = {2024-04-09T00:13:29.000+0200}, title = {REBEL: A Regularization-Based Solution for Reward Overoptimization in Reinforcement Learning from Human Feedback.}, url = {http://dblp.uni-trier.de/db/journals/corr/corr2312.html#abs-2312-14436}, volume = {abs/2312.14436}, year = 2023 }