原书出处
Build a Reasoning Model (From Scratch)
all rollouts receive the same reward (for example, force all rewards to 0.0 or all to 1.0). Run the advantage computation and verify that the resulting GRPO loss is zero. Why is this behavior desirable in group-relative policy optimization?
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