# SGLang and Miles host a reinforcement learning training session with NVIDIA

> Original title: Run a real reinforcement learning training loop with @NVIDIAAI and the latest SGLang + Miles!

- Source: SGLang
- Published: 2026-11-04T20:57:07.000Z
- Bad Influence: https://badinfluence.news/items/j4458w70ho5u78zij16fctcj9
- Original: https://x.com/sgl_project/status/2118085153306366094

## Summary

SGLang invites developers to a live session on running a reinforcement learning training loop with NVIDIA, using SGLang for rollout generation and Miles for policy training. The session covers live weight syncing between the two systems and engineering choices for faster, more stable RL training, with a path to larger models and more complex tasks. Registration is open through a Luma link.

## Post

Run a real reinforcement learning training loop with @NVIDIAAI and the latest SGLang + Miles!

Use SGLang to generate rollouts, Miles to train the policy, and live weight syncing to connect them. Learn the engineering choices that make RL training faster and more stable, then explore how to scale the same workflow to larger models and more complex tasks.

Reserve your spot: https://luma.com/o53t6tvs 

🧵 2/7