AI Roadmaps
← All roadmaps
AdvancedRoadmap 42 · 10 steps · 6h 07m of video

World Models

Models that learn how an environment responds to actions, then plan or train agents inside it: model-based RL, Dreamer, MuZero, Genie, world foundation models, and JEPA-style planning.

Before this: Reinforcement Learning and Generative AI: Images & Video. Self-Supervised & Contrastive Learning helps for the JEPA steps.

  1. 29 min
    Step 1

    What world models are

    The core idea: a learned model that predicts how a world changes after an action.

    But what exactly are world models?

    Julia Turc

  2. 18 min
    Step 2

    Model-based reinforcement learning

    Learn a dynamics model from experience, then use it to plan or improve a policy.

    L6 Model-based RL (Foundations of Deep RL Series)

    Pieter Abbeel

  3. 19 min
    Step 3

    World Models (Ha and Schmidhuber, 2018)

    A VAE compresses frames, an RNN predicts the next latent, a tiny controller acts.

    World Models

    Yannic Kilcher

    ctallec/world-models★ 721
  4. 55 min
    Step 4

    Dreamer: learn behaviour inside the model

    DreamerV2 trains its actor and critic on imagined latent rollouts, mastering Atari.

    Dreamer v2: Mastering Atari with Discrete World Models (Machine Learning Research Paper Explained)

    Yannic Kilcher

    danijar/dreamerv2★ 1.1k
  5. 34 min
    Step 5

    MuZero: plan with a learned model

    Its author explains a model that predicts reward, value, and policy, not pixels.

    MuZero - ICAPS 2020

    Julian Schrittwieser

    werner-duvaud/muzero-general★ 2.9k
  6. 1h 01m
    Step 6

    Genie: worlds you can walk through

    The Genie 3 team on generating frames in real time from a user's actions.

    Genie 3: An infinite world model | Shlomi Fruchter and Jack Parker-Holder

    Google DeepMind

  7. 13 min
    Step 7

    World foundation models

    Large video-trained models used to generate training data and test robots and cars.

    World Foundation Models - Computerphile

    Computerphile

  8. 36 min
    Step 8

    NVIDIA Cosmos, an overview

    NVIDIA's GTC 2025 introduction to its open world foundation model platform.

    An Introduction to NVIDIA Cosmos World Foundational Models | NVIDIA GTC 2025

    NVIDIA Developer

  9. 59 min
    Step 9

    Predict in representation space: LeCun's case

    Why LeCun argues world models should predict abstract features, not every pixel.

    Yann LeCun: World Models: Enabling the next AI revolution

    Computer Vision and Geometry Group, ETH Zurich

  10. 44 min
    Step 10

    V-JEPA 2: plan robot actions

    A self-supervised video model gets an action-conditioned predictor for robot planning.

    Introduction to World Models: V-JEPA 2

    YanAITalk

    facebookresearch/vjepa2★ 4.9k

Build it

Watching isn't learning. Pick one and put it on GitHub.

Browse all roadmaps →