Huge thanks to @carlosferrazza.bsky.social and Pieter for their great supervision and for hosting me at Berkeley over the past 5 months!
17.12.2024 17:48
👍 2
🔁 0
💬 0
📌 0
Huge thanks to @carlosferrazza.bsky.social and Pieter for their great supervision and for hosting me at Berkeley over the past 5 months!
Excited to share MaxInfoRL, a family of powerful off-policy RL algorithms! The core focus of this work was to develop simple, flexible, and scalable methods for principled exploration. Check out the thread below to see how MaxInfoRL meets these criteria while also achieving SOTA empirical results.