Verl Hybrid Engine Reinforcement Learning

Reinforcement learning framework (PPO, GRPO) for post-training large language models.

robertoatila Updated 9 repo stars
J.A.R.V.I.S. — Autonomous Cognitive Runtime

File contents

robertoatila/jarvis-skill-registry commit b53c04ab3e

Frequently asked questions

npx get-skill add robertoatila/verl-hybrid-engine-reinforcement-learning