Awesome RL with Human Feedback / 2023 / arXiv

Aligning Language Models with Offline Reinforcement Learning from Human Feedback

作者：Jian Hu, Li Tao, June Yang, Chandler Zhou · 来源：arXiv · 发布日期：2023

偏好学习对齐目标设计策略优化离线人类反馈强化学习人类反馈设计
新标签打开 AlphaXiv
Aligning Language Models with Offline Reinforcement Learning from Human Feedback figure
AlphaXiv 中文概览（可滚动查看）