Reward Calibration for Continual Reinforcement Learning from Human Feedback

Joachim Lang, Jiahao Zhao, Linjing Li, Daniel ZengCommunications 2025 · DOI · OpenAlex

BibTeX
@inproceedings{lang2025reward,
  author = {Joachim Lang and Jiahao Zhao and Linjing Li and Daniel Zeng and Daniel Dajun Zeng},
  title = {{Reward Calibration for Continual Reinforcement Learning from Human Feedback}},
  booktitle = {Communications},
  year = {2025},
  doi = {10.1007/978-981-95-4094-5\_14},
}

Loading related content...

Figure