Awesome RL with Human Feedback / 2023 / arXiv

Fantastic Rewards and How to Tame Them: A Case Study on Reward Learning for Task-oriented Dialogue Systems

作者：Yihao Feng*, Shentao Yang*, Shujian Zhang, Jianguo Zhang, Caiming Xiong, Mingyuan Zhou, Huan Wang · 单位：Salesforce Research, The University of Texas at Austin · 来源：arXiv · 发布日期：2023

奖励规范奖励建模框架/系统长文本/对话
新标签打开 AlphaXiv新标签打开 Code
Fantastic Rewards and How to Tame Them: A Case Study on Reward Learning for Task-oriented Dialogue Systems figure
AlphaXiv 中文概览（可滚动查看）