Agent Skills: grpo

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.

ID: benchflow-ai/skillsbench/grpo

Repository

benchflow-aiLicense: Apache-2.0
1,819369

Install this agent skill to your local

npx skills add benchflow-ai/skillsbench --skill grpo

Skill Files

The files that make up grpo.

Download Skill

More agent skills