%0 Journal Article %1 journals/corr/abs-2403-17031 %A Huang, Shengyi %A Noukhovitch, Michael %A Hosseini, Arian %A Rasul, Kashif %A Wang, Weixun %A Tunstall, Lewis %D 2024 %J CoRR %K dblp %T The N+ Implementation Details of RLHF with PPO: A Case Study on TL;DR Summarization. %U http://dblp.uni-trier.de/db/journals/corr/corr2403.html#abs-2403-17031 %V abs/2403.17031

@article{journals/corr/abs-2403-17031, added-at = {2024-04-10T00:00:00.000+0200}, author = {Huang, Shengyi and Noukhovitch, Michael and Hosseini, Arian and Rasul, Kashif and Wang, Weixun and Tunstall, Lewis}, biburl = {https://www.bibsonomy.org/bibtex/235c1c21700df33f0176ee295057f42b2/dblp}, ee = {https://doi.org/10.48550/arXiv.2403.17031}, interhash = {bd3fedb1af039aafd3f3d356c6e1af0b}, intrahash = {35c1c21700df33f0176ee295057f42b2}, journal = {CoRR}, keywords = {dblp}, timestamp = {2024-04-12T14:37:10.000+0200}, title = {The N+ Implementation Details of RLHF with PPO: A Case Study on TL;DR Summarization.}, url = {http://dblp.uni-trier.de/db/journals/corr/corr2403.html#abs-2403-17031}, volume = {abs/2403.17031}, year = 2024 }