# MIT course lecture walks through RL and self-distillation for LLM training

> Original title: MIT《How to AI an AI》第 6 讲：从 PPO、GRPO 到同策略蒸馏，大模型强化学习怎样在工程上真正跑起来

- Source: meng shao
- Published: 2026-11-09T06:17:19.000Z
- Bad Influence: https://badinfluence.news/items/o27hc00deznuojtk5g85d7hv1
- Original: https://x.com/shao__meng/status/2119675683836416068

## Summary

MIT's MAS.S62 lecture 6, taught by Idan Shenfeld of Thinking Machines Lab, covers running reinforcement learning on LLMs with PPO, GRPO, and on-policy distillation. The lecture contrasts on-policy distillation, which gives a score per token, with RL's single reward per response, and describes the five steps of one training update. It also lists the training curves to monitor and shows how to run the verl framework, then compares it with the reef online-learning server.

## Post

https://x.com/i/article/2119672556039143424