A Distributional Approach to Uncertainty-Aware Preference Alignment Using Offline Demonstrations

Sheng Xu, Bo Yue, Hongyuan Zha, Guiliang Liu

2/12/2026

No official code found. Best implementation: Jasonxu1225/Uncertainty-aware-Preference-based-Reinforcement-Learning (7 stars, MIT, last commit 2025-11-11).

Semantic Scholar

Code Implementations(1)

Jasonxu1225/Uncertainty-aware-Preference-based-Reinforcement-LearningCommunity67%

MIT

[ICLR 2025] ''A Distributional Approach to Uncertainty-Aware Preference Alignment Using Offline Demonstrations'' Official Code

70Shell, PythonFeb 28, 202511 months agoMIT

Cite this paper

@article{xu2026distributional,
  title  = {A Distributional Approach to Uncertainty-Aware Preference Alignment Using Offline Demonstrations},
  author = {Sheng Xu and Bo Yue and Hongyuan Zha and Guiliang Liu},
  year   = {2026},
  url    = {https://api.semanticscholar.org/CorpusID:9aef3067701169c20be1b82b4d0c197b71c50622},
  journal = {ICLR 2025 2025}
}

A Distributional Approach to Uncertainty-Aware Preference Alignment Using Offline Demonstrations

Code Implementations(1)

Cite this paper

Discussion