Three RL Tricks for Reasoning LMs Collapse to One Std‑Dev Dial
GRPO, Dr. GRPO, and DAPO—methods behind state‑of‑the‑art reasoning models—are mathematically the same operation: scaling updates by the group standard deviation of reward across sampled answers. This identity shows that the key learning signal is the disagreement‑based std‑dev dial, guiding which problems get the most training impact.