Ted Moskovitz, Aaditya K. Singh, DJ Strouse, Tuomas Sandholm, Ruslan Salakhutdinov, Anca D. Dragan, Stephen Marcus McAleer. Confronting Reward Model Overoptimization with Constrained RLHF. In The Twelfth International Conference on Learning Representations, ICLR 2024, Vienna, Austria, May 7-11, 2024. OpenReview.net, 2024. [doi]
@inproceedings{MoskovitzSSSSDM24,
title = {Confronting Reward Model Overoptimization with Constrained RLHF},
author = {Ted Moskovitz and Aaditya K. Singh and DJ Strouse and Tuomas Sandholm and Ruslan Salakhutdinov and Anca D. Dragan and Stephen Marcus McAleer},
year = {2024},
url = {https://openreview.net/forum?id=gkfUvn0fLU},
researchr = {https://researchr.org/publication/MoskovitzSSSSDM24},
cites = {0},
citedby = {0},
booktitle = {The Twelfth International Conference on Learning Representations, ICLR 2024, Vienna, Austria, May 7-11, 2024},
publisher = {OpenReview.net},
}