界面已本地化;技能介绍与说明文档按所选语言由 AI 自动翻译,代码、命令、路径和专业术语保留原文,以原作者文档为准。
探索技能
部署与运维 · SKILL.md

sage-self-hinting-rl

sage-self-hinting-rl

【部署与运维】Inject privileged hints during GRPO training to reshape rollout distributions when advantage collapses occur, increasing outcome diversity without changing task rewards. Hints removed at deployment; policy automatically learns when to use hints via online refresh mechanism.

独立 GitHub 快照 · 自动分类 · 以原作者文档为准

Aadu2021 / skillxivNOASSERTION

技能说明

GitHub
正在从源仓库读取说明…
我的收藏