Reinforcement Learning from Human Feedback - Progress and Challenges

Reinforcement Learning from Human Feedback - Progress and Challenges

UC Berkeley EECS via YouTube Direct link

Introduction

1 of 23

1 of 23

Introduction

Class Central Classrooms beta

YouTube videos curated by Class Central.

Classroom Contents

Reinforcement Learning from Human Feedback - Progress and Challenges

Automatically move to the next video in the Classroom when playback concludes

  1. 1 Introduction
  2. 2 Overview
  3. 3 Hallucination
  4. 4 Conceptual Model
  5. 5 Behavior Cloning
  6. 6 Does the model know
  7. 7 Uncertainty
  8. 8 When should you hedge
  9. 9 Long form answers
  10. 10 Improving factuality
  11. 11 Challenges
  12. 12 Retrieval Citing Sources
  13. 13 RL Environment
  14. 14 RL Task
  15. 15 RL Pipeline
  16. 16 Browsing
  17. 17 Dagger
  18. 18 Open problems
  19. 19 Scalable oversight
  20. 20 Optimization for correctness
  21. 21 Creativity
  22. 22 Classical Literature Philosophy
  23. 23 AI Progress Forecasting

Never Stop Learning.

Get personalized course recommendations, track subjects and courses with reminders, and more.

Someone learning on their laptop while sitting on the floor.