Generalized on-policy distillation with reward extrapolation | Dark Hacker News

Dark Hacker News

new|best|ask|show|jobs

Built with the HackerNews API. Developed by LJT.AI

Note: The HackerNews API provides up to 500 stories per category

Generalized on-policy distillation with reward extrapolation(arxiv.org)

3 points by fzliu 93 days ago | 0 comments

No comments yet

Generalized on-policy distillation with reward extrapolation | Dark Hacker News