Sign up
Sign in
1. https://arxiv.org/pdf/2106.02039.pdf from Levine's group. I find this one cool because it actually fundamentally explains how RL problems can be reframed as sequence modeling problems.
Harry Zhang
Quentin Gallouédec
Follow
--
Share
Thank you for sharing this !
PhD student in reinforcement learning. https://gallouedec.com
Help
Status
About
Careers
Press
Blog
Privacy
Terms
Text to speech
Teams
