原书出处
Build a Reasoning Model (From Scratch)
will use the group relative policy optimization (GRPO) algorithm for policy optimization. In short, RLVR determines what learning signal is available, and GRPO determines how that signal is used to update the model weights. Policy gradient algorithms A widely used policy gradient algorithm for LLMs is proximal policy optimization (PPO), which was popularized in RLHF. In principle, the same algorithm could also be applied in
原书定位详情
来源:a19c7933-4eda-4176-aebd-30fe7e1ad292
正文位置:extracted/Build a Reasoning Model (From Scratch)/_epub-src/OEBPS/Text/chapter-6.html
EPUB SHA-256:52d4d07986020be70f5aac21762dfcf60fcba08db0ba29d4f63957caf12aa377