AI & Machine Learning
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.
- Publisher / source
- benchflow-ai/skillsbench (found on GitHub top repositories)
- Upstream record
- benchflow-ai/skillsbench
- Version
- Version 1
- Published
- Publication review
- Approved for publication · recorded passed scan 2026-11-08
- Content fingerprint
90ef5f123f4b6107d85c69d53d6878aec29e5c08950dc52b9bd6fd872187804c