The World Models Series
This series collects my learning notes on world models. I am using it to connect several threads that I keep running into: reinforcement learning, learned dynamics, latent representations, JEPA-style prediction, planning, uncertainty, and model editing or unlearning.
The main question I want to understand is simple to say but hard to answer:
When does a learned model of the world become reliable enough to support decisions, planning, and intervention?
Reading Order
-
Reinforcement Learning and Abstract World Models
This is the foundation note. It starts from reinforcement learning and Bellman equations, then moves toward world models, abstract latent-space world models, JEPA-style prediction, and reward hacking. I use this post as the mathematical map before going into specific architectures.
-
LeWorldModel: A Compact Latent World Model—and Where It Breaks
This is the first case study. It looks at LeWorldModel as a compact action-conditioned JEPA for planning from pixels, then focuses on the failure modes that matter for reliable control: counterfactual coverage, uncertainty, memory, rollout error, and planners exploiting their own learned model.
Notes To Expand Later
I expect this series to grow around a few recurring questions:
- how much of a world model should be learned from pixels, latent states, rewards, language, or simulation;
- how to tell whether a latent representation preserves the state distinctions that planning actually needs;
- how uncertainty, memory, and counterfactual data coverage change the reliability of model-based control;
- how to edit, unlearn, or localize a transition belief without damaging unrelated dynamics.
For now, these two posts are the starting point: one for the basic mathematical frame, and one for a concrete latent-world-model case study.
Enjoy Reading This Article?
Here are some more articles you might like to read next: