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