Gaon An, Junhyeok Lee, Xingdong Zuo, Norio Kosaka, Kyung Min Kim, Hyun Oh Song. Direct Preference-based Policy Optimization without Reward Modeling. In Alice Oh, Tristan Naumann, Amir Globerson, Kate Saenko, Moritz Hardt, Sergey Levine, editors, Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, NeurIPS 2023, New Orleans, LA, USA, December 10 - 16, 2023. 2023. [doi]
@inproceedings{AnLZKKS23, title = {Direct Preference-based Policy Optimization without Reward Modeling}, author = {Gaon An and Junhyeok Lee and Xingdong Zuo and Norio Kosaka and Kyung Min Kim and Hyun Oh Song}, year = {2023}, url = {http://papers.nips.cc/paper_files/paper/2023/hash/de8bd6b2b01cfa788e63f62e5b9a99b9-Abstract-Conference.html}, researchr = {https://researchr.org/publication/AnLZKKS23}, cites = {0}, citedby = {0}, booktitle = {Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, NeurIPS 2023, New Orleans, LA, USA, December 10 - 16, 2023}, editor = {Alice Oh and Tristan Naumann and Amir Globerson and Kate Saenko and Moritz Hardt and Sergey Levine}, }