Why it matters
GRPO enabled DeepSeek R1's reasoning. Efficient for reasoning training. Understanding shapes methods.
Advertisement
The architecture
Sample N completions per prompt.
Advantage: normalized within group.
PPO clip + KL.
Advertisement
How it works end to end
Advantage: (r_i - mean(r)) / std(r).
PPO-style clipping.
KL to reference.
No separate value model.