# Lambert highlights importance sampling methods for RL train-inference mismatch

> Original title: Was reading the score-centering RL paper to add some notes on it the my book, and they have a great table in the appendix on the differen...

- Source: Nathan Lambert
- Published: 2026-10-30T20:49:26.000Z
- Bad Influence: https://badinfluence.news/items/zrj639fey9cqdsfuao97z514k
- Original: https://x.com/natolambert/status/2116271281351881120

## Summary

Nathan Lambert says he was reading a score-centering RL paper for notes in his book and found a table in its appendix comparing importance-sampling methods for train-inference mismatch in RL. He argues these methods have been the main focus of RL algorithm research since the GRPO takeoff.

## Post

Was reading the score-centering RL paper to add some notes on it the my book, and they have a great table in the appendix on the different importance sampling based train-inference mismatch methods in RL. These have been the biggest focus of RL algorithm research since the GRPO takeoff, imo.

![](https://badinfluence.news/api/img-proxy?u=https%3A%2F%2Fpbs.twimg.com%2Fmedia%2FHV6Bg_2WQAA5p6R.jpg&mode=thumb&exp=1793664000&sig=21faabe79465c989)