Awesome RL with Human Feedback / 2024 / arXiv

DPO Meets PPO: Reinforced Token Optimization for RLHF

作者：Han Zhong, Zikang Shan, Guhao Feng, Wei Xiong, Xinle Cheng, Li Zhao, Di He, Jiang Bian, Liwei Wang · 来源：arXiv · 发布日期：2024

奖励建模策略优化策略梯度人类反馈强化学习信用分配/密集奖励
新标签打开 AlphaXiv新标签打开 Code
DPO Meets PPO: Reinforced Token Optimization for RLHF figure
AlphaXiv 中文概览（可滚动查看）