TheSequence

TheSequence

Share this post

TheSequence
TheSequence
Edge 291: Reinforcement Learning with Human Feedback
Copy link
Facebook
Email
Notes
More

Edge 291: Reinforcement Learning with Human Feedback

1) Reinforcement Learning with Human Feedback(RLHF) 2) The RLHF paper, 3) The transformer reinforcement learning framework.

May 16, 2023
∙ Paid
30

Share this post

TheSequence
TheSequence
Edge 291: Reinforcement Learning with Human Feedback
Copy link
Facebook
Email
Notes
More
Share
Created Using Midjourney

In this Issue:

  • Reinforcement Learning with Human Feedback(RLHF)

  • The RLHF paper.

  • The transformer reinforcement learning framework.

💡 ML Concept of the Day: Reinforcement Learnign with Human Feedback

One of the key improvements in models like ChatGPT or GPT-4 relative to its predecessors has been their ability to follow instructions. The genesis of this capability has its roots on a technique known as reinforcement learning with human feedback(RLHF) outlined in a 2017 paper. The core idea of RLHF is to extend LLM’s core feature of predicting the next word with the ability of understanding and fulfilling human requests. This is done by reformulating language tasks as a reinforcement learning problem.

This post is for paid subscribers

Already a paid subscriber? Sign in
© 2025 Jesus Rodriguez
Privacy ∙ Terms ∙ Collection notice
Start writingGet the app
Substack is the home for great culture

Share

Copy link
Facebook
Email
Notes
More