World Models and Model-Based RL Reading List

Curated by Mouhssine Rifaki | Stanford Electrical Engineering | Last updated August 2026

Learning a model of the environment and planning inside it. From Dyna to modern latent-space world models.

World Models and Model-Based RL: 10 key papers

1. World Models
   Ha and Schmidhuber. arXiv 2018.
2. Dream to Control: Learning Behaviors by Latent Imagination
   Hafner et al. arXiv 2019.
3. Mastering Atari with Discrete World Models
   Hafner et al. arXiv 2020.
4. Learning Latent Dynamics for Planning from Pixels
   Hafner et al. arXiv 2018.
5. Transformers are Sample-Efficient World Models
   Micheli et al. arXiv 2022.
6. Model-Based Reinforcement Learning for Atari
   Kaiser et al. arXiv 2019.
7. Temporal Predictive Coding For Model-Based Planning In Latent Space
   Nguyen et al. arXiv 2021.
8. DayDreamer: World Models for Physical Robot Learning
   Wu et al. arXiv 2022.
9. Genie: Generative Interactive Environments
   Bruce et al. arXiv 2024.
10. TD-MPC2: Scalable, Robust World Models for Continuous Control
    Hansen et al. arXiv 2023.

Related reading lists

• Model-Based Reinforcement Learning
• Monte Carlo Tree Search
• Curiosity-Driven Exploration
• Sample Complexity in Reinforcement Learning
• Classical Planning & Search Algorithms
• Robust & Risk-Sensitive RL
• Sim-to-Real Transfer
• Data Augmentation for Reinforcement Learning