
Dylan Foster 🐢
@canondetortugas
Researcher in ML/RL Theory @MSFTResearch. Previously @MIT @Cornell_CS
djfoster.bsky.social
RL Theory Lecture Notes: arxiv.org/abs/2312.16730
ID: 470917917
https://www.dylanfoster.net/ 22-01-2012 09:02:20
180 Tweet
2,2K Followers
931 Following



Minqi Jiang I think it also shows how bad the existing exploration methods are. RL works now because pretraining did the hard part of exploration for it. There could be some room in figuring out how to put more compute into more efficient exploration during RL beyond just sampling more.

