Preference Optimization as Probabilistic Inference
Mentioned in DreamerV4 paper.
Citation
(Abdolmaleki et al., 2024)
Abdolmaleki, A., Piot, B., Shahriari, B., Springenberg, J. T., Hertweck, T., Joshi, R., Oh, J., Bloesch, M., Lampe, T., Heess, N., Buchli, J., & Riedmiller, M. (2024). Preference Optimization as Probabilistic Inference. https://arxiv.org/pdf/2410.04166v1