Mastering Atari with Discrete World Models - Machine Learning Research Paper Explained

Mastering Atari with Discrete World Models - Machine Learning Research Paper Explained

Yannic Kilcher via YouTube Direct link

- KL Balancing

14 of 19

14 of 19

- KL Balancing

Class Central Classrooms beta

YouTube videos curated by Class Central.

Classroom Contents

Mastering Atari with Discrete World Models - Machine Learning Research Paper Explained

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

  1. 1 - Intro & Overview
  2. 2 - Short Recap of Reinforcement Learning
  3. 3 - Problems with Model-Free Reinforcement Learning
  4. 4 - How World Models Help
  5. 5 - World Model Learner Architecture
  6. 6 - Deterministic & Stochastic Hidden States
  7. 7 - Latent Categorical Variables
  8. 8 - Categorical Variables and Multi-Modality
  9. 9 - Sampling & Stochastic State Prediction
  10. 10 - Actor-Critic Learning in Dream Space
  11. 11 - The Incompleteness of Learned World Models
  12. 12 - How General is this Algorithm?
  13. 13 - World Model Loss Function
  14. 14 - KL Balancing
  15. 15 - Actor-Critic Loss Function
  16. 16 - Straight-Through Estimators for Sampling Backpropagation
  17. 17 - Experimental Results
  18. 18 - Where Does It Fail?
  19. 19 - Conclusion

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.