Adaptive Confidence-aware Preference-based Reinforcement Learning with Noisy Feedback.

@inproceedings{gong-2025-adaptive, author = {Yuhao Gong and Zhenbo Lu and Wanxuan Lu and Wengang Zhou and Houqiang Li}, editor = {Guodong Long and Michale Blumestein and Yi Chang and Liane Lewin-Eytan and Zi Huang and Elad Yom-Tov}, title = {{Adaptive Confidence-aware Preference-based Reinforcement Learning with Noisy Feedback}}, booktitle = {{Companion Proceedings of the ACM on Web Conference 2025, WWW 2025, Sydney, NSW, Australia, 28 April 2025 - 2 May 2025}}, pages = {2120--2128}, publisher = {ACM}, year = {2025}, url = {https://doi.org/10.1145/3701716.3717570}, doi = {https://doi.org/10.1145/3701716.3717570} }