This is one of chelsea’s papers that talks about unifying RLHF for robotics.

It cites some papers on how RLHF is done.

Citation

(Rafailov et al., 2024)

Rafailov, R., Hejna, J., Park, R., & Finn, C. (2024). From r to Q^*: Your Language Model is Secretly a Q-Function. https://arxiv.org/pdf/2404.12358