domains / families / science / grpo

grpo

separate

Reference for the GRPO (Group Relative Policy Optimization) algorithm. Use when implementing, debugging, or verifying a GRPO training pipeline — covers the mathematical formulation (group-relative advantages, clipped surrogate loss, KL penalty), the training loop (generate → score → advantage → loss), log-probability computation, advantage estimation, and relationship to PPO/REINFORCE.

When to use

• implementing GRPO training pipeline
• debugging GRPO training pipeline
• verifying GRPO training pipeline
• mathematical formulation
• group-relative advantages
• clipped surrogate loss
• KL penalty
• training loop

Skill page

Source