#

v-trace

Here is 1 public repository matching this topic...

deadsmash07 / rac-rlxf-code

Retroactive Advantage Correction (RAC): closed-form V-trace bias correction for delay-aware RLHF — RLxF Workshop @ ICML 2026

reinforcement-learning ppo off-policy v-trace delayed-rewards rlhf

Updated Jun 19, 2026
Python

Improve this page

Add a description, image, and links to the v-trace topic page so that developers can more easily learn about it.

Curate this topic

Add this topic to your repo

To associate your repository with the v-trace topic, visit your repo's landing page and select "manage topics."