Awesome RL with Human Feedback / 2024 / arXiv

RLHF Workflow: From Reward Modeling to Online RLHF

作者：Hanze Dong, Wei Xiong, Bo Pang, Haoxiang Wang, Han Zhao, Yingbo Zhou, Nan Jiang, Doyen Sahoo, Caiming Xiong, Tong Zhang · 单位：Salesforce AI Research, University of Illinois Urbana-Champaign · 来源：arXiv · 发布日期：2024

奖励建模偏好学习在线人类反馈强化学习框架/系统
新标签打开 AlphaXiv新标签打开 Code
RLHF Workflow: From Reward Modeling to Online RLHF figure
AlphaXiv 中文概览（可滚动查看）