Yihua Zhang
EN 中

Series

The GRPO lineage

Reading order

DeepSeek-R1 Dissection: Understanding PPO & GRPO Without Any Prior Reinforcement Learning Knowledge
Post-training · en / zh ·16 equations The GRPO lineage 1 GRPORLHF
From GRPO to DAPO and GSPO: What, Why and How
Post-training · en / zh ·18 equations The GRPO lineage 2 GRPO
Re-understanding KL Approximation from an RL-for-LLM Lens: Notes on “Approximating KL Divergence
Post-training · en / zh ·18 equations The GRPO lineage 3 GRPO