Skip to content
/ Online_RLHF Public

A PyTorch implementation of the paper "Provably Efficient RLHF Pipeline: A Unified View from Contextual Bandits". This repository provides a flexible and modular approach to Reinforcement Learning from Human Feedback (RLHF).

5 stars 1 fork Branches Tags Activity
Star
Notifications You must be signed in to change notification settings

ZinYY/Online_RLHF

Error
Looks like something went wrong!

About

A PyTorch implementation of the paper "Provably Efficient RLHF Pipeline: A Unified View from Contextual Bandits". This repository provides a flexible and modular approach to Reinforcement Learning from Human Feedback (RLHF).

Resources

Readme
Activity

Stars

5 stars

Watchers

1 watching

Forks

1 fork
Report repository

Releases

No releases published

Packages

No packages published

Languages