返回探索

探讨Jev模型作为PRL评判者

帖子询问是否有人将Jev风格模型用作过程奖励学习(PRL)中的评判者,并指出更好的评判者可能推动PRL复兴,更多监督有助于学习。

has anyone used Jev-style models as judges in Process Reward Learning (PRL)? It seems like PRL could make a comeback if we have better judges. And more supervision leads to better learning.

探讨Jev模型作为PRL评判者 1
· 0 次赞在 X 打开