Skip to content
Better HN
Top
New
Best
Ask
Show
Jobs
Search
⌘K
Generalized on-policy distillation with reward extrapolation | Better HN
Generalized on-policy distillation with reward extrapolation
(opens in new tab)
(arxiv.org)
3 points
fzliu
1mo ago
0 comments
Share
0 comments
No comments yet.
