Awesome RL with Human Feedback / 2024 / arXiv

Improving Reinforcement Learning from Human Feedback with Efficient Reward Model Ensemble

作者：Shun Zhang, Zhenfang Chen, Sunli Chen, Yikang Shen, Zhiqing Sun, Chuang Gan · 单位：MIT-IBM Watson AI Lab, Tsinghua University, Carnegie Mellon University · 来源：arXiv · 发布日期：2024

奖励建模偏好学习样本效率人类反馈设计
新标签打开 AlphaXiv
Improving Reinforcement Learning from Human Feedback with Efficient Reward Model Ensemble figure
AlphaXiv 中文概览（可滚动查看）