// ◐ World Models & Self-Supervised Learning
World Models
Learn a dreamable environment model, then train the policy inside it.
世界模型（Ha & Schmidhuber） 2018 Intermediate core
IN PLAIN WORDS
A VAE compresses frames, an RNN predicts the next latent, and a tiny controller learns inside the dream. It revived world-model research.
Used in: Starting point for world-model research
TIMELINE · prerequisites → this → what builds on it
01Original paper
02Where it sits
Learn the left column first; the right column builds on this one.
World Models
Then you can learn
Related:Joint-Embedding Predictive Architecture (JEPA)
Left: prerequisites · right: builds on this · dashed: related. Full map →
03Learning resources
Official docs, explainers, courses and reference code. All links checked.
Official docs
04Where the course teaches it
On learning paths:Generative Models & Frontier Research
For AI / data
- Verification: verified, checked 2026-10-21.
- JSON: /api/learn/algorithms.json (id:
world-models)