Experience replay is the backbone of off-policy RL.
But here's a question:
Which experiences should you replay?
New paper: 𝐕𝐋𝐌-𝐆𝐮𝐢𝐝𝐞𝐝 𝐄𝐱𝐩𝐞𝐫𝐢𝐞𝐧𝐜𝐞 𝐑𝐞𝐩𝐥𝐚𝐲
Project page: esharony.me/projects/vlm...
🧵
Elad Sharony
@eladsharony.bsky.social
1 followers 2 following 13 posts
Ph.D. Student - Electrical & Computer Engineering - Technion | (RL)² Lab esharony.me