Reinforcement Learning · advanced · concept 131 of 176

📊GRPO (Group Relative Policy Optimization)

A reinforcement learning algorithm that simplifies PPO by dropping the value network: it samples a group of responses per prompt and scores each one against the group average. Introduced in DeepSeekMath and used to train DeepSeek-R1, it became a standard recipe for training reasoning models on verifiable rewards like math and unit tests.