AI 导读
好帖，闭源实验室用的一些 RL 细节正慢慢泄露出来。
正文
Nice thread, some RL details used by closed labs slowly leaking out.
Tinker's new StableReinforce objective is Reinforce + Score Centering. Here's how I reverse-engineered it 🧵在 X 查看被引用的帖子
来源：Nathan Lambert · x.com