站内快照 · 国内可打开。外网原文可能无法访问。

• 论文公开站arXiv2026年10月5日 2:13

  Planning to Learn

  Policy-gradient methods are central to modern reinforcement learning, including LLM post-training. When they struggle, the usual suspects are exploration, credit assignment and action-sampling noise. Classification has none of them. A classifier is a policy whose expected reward,

  原文链接