Straight from the HF archives: @krasul giving us a masterclass on the math behind score centering for stable RL
Hugging Face shares video on score centering for stable RL training
AILewis Tunstall of Hugging Face shares a YouTube video in which @krasul explains the math behind score centering for stable reinforcement learning. The post provides only the video link and does not include further technical details.
Lewis TunstallVerified on X
@_lewtun
Source details
Lewis Tunstall · x.comPublished · added here
Original title: Straight from the HF archives: @krasul giving us a masterclass on the math behind score centering for stable RL