A systematic comparison of GRPO and its descendants — CLIP-DAPO, CISCO, DAPO, Dr. GRPO, GDPO, REINFORCE++ — what each fixes, what trade-offs each makes, and when to use which.
A systematic comparison of GRPO and its descendants — CLIP-DAPO, CISCO, DAPO, Dr. GRPO, GDPO, REINFORCE++ — what each fixes, what trade-offs each makes, and when to use which.
PPO and GRPO loss functions annotated term-by-term — the clipped surrogate, GAE, value loss, entropy bonus, and group-normalised advantages — with links to the posts explaining each design choice.
PPO and GRPO loss functions annotated term-by-term — the clipped surrogate, GAE, value loss, entropy bonus, and group-normalised advantages — with links to the posts explaining each design choice.
GRPO achieves competitive alignment results without a value function. Here's exactly what changes in the math and implementation, and why that matters for training efficiency and stability.
GRPO achieves competitive alignment results without a value function. Here's exactly what changes in the math and implementation, and why that matters for training efficiency and stability.