Chelsea Finn @chelseabfinn · 09 Aug 2026
Pretraining a Q-function often doesn’t actually help RL finetuning, compared to initializing Q from scratch. We find that pretraining Q-functions on data from diverse policies is critical to see improvements from pretraining. Paper: https://t.co/dlj5RXVFED
77 912Views
641Likes
54Reposts
13Replies
6Quotes
550Bookmarks
Is that a lot?
1.12×vs this author's median69 350 views is typical
71Percentile for this authorof 7 recent posts
3.52×vs 100K–1M median22 159 views is typical
76.91%Reachviews ÷ followers
0.92%Engagement rateof viewers reacted