Awesome RL with Human Feedback / 2024 / arXiv

Dataset Reset Policy Optimization for RLHF

作者：Jonathan D. Chang, Wenhao Zhan, Owen Oertell, Kianté Brantley, Dipendra Misra, Jason D. Lee, Wen Sun · 单位：Department of Computer Science, Cornell University, Department of Electrical and Computer Engineering, Princeton University · 来源：arXiv · 发布日期：2024

策略优化数据筛选
新标签打开 AlphaXiv新标签打开 Code
Dataset Reset Policy Optimization for RLHF figure
AlphaXiv 中文概览（可滚动查看）