%0 Journal Article %1 journals/corr/abs-2402-09345 %A Miao, Yuchun %A Zhang, Sen %A Ding, Liang %A Bao, Rong %A Zhang, Lefei %A Tao, Dacheng %D 2024 %J CoRR %K dblp %T Mitigating Reward Hacking via Information-Theoretic Reward Modeling. %U http://dblp.uni-trier.de/db/journals/corr/corr2402.html#abs-2402-09345 %V abs/2402.09345

@article{journals/corr/abs-2402-09345, added-at = {2024-07-19T00:00:00.000+0200}, author = {Miao, Yuchun and Zhang, Sen and Ding, Liang and Bao, Rong and Zhang, Lefei and Tao, Dacheng}, biburl = {https://www.bibsonomy.org/bibtex/288a76a1cca0476c2d8d1970ee38e2a5c/dblp}, ee = {https://doi.org/10.48550/arXiv.2402.09345}, interhash = {56cd8f9b514d593834af15625c7e1a4d}, intrahash = {88a76a1cca0476c2d8d1970ee38e2a5c}, journal = {CoRR}, keywords = {dblp}, timestamp = {2024-07-22T07:11:01.000+0200}, title = {Mitigating Reward Hacking via Information-Theoretic Reward Modeling.}, url = {http://dblp.uni-trier.de/db/journals/corr/corr2402.html#abs-2402-09345}, volume = {abs/2402.09345}, year = 2024 }