Simple, Good, Fast: Self-Supervised World Models Free of Baggage
Abstract
What are the essential components of world models? How far do we get with world models that are not employing RNNs, transformers, discrete representations, and image reconstructions? This paper introduces SGF, a Simple, Good, and Fast world model that uses self-supervised representation learning, captures short-time dependencies through frame and action stacking, and enhances robustness against model errors through data augmentation. We extensively discuss SGF’s connections to established world models, evaluate the building blocks in ablation studies, and demonstrate good performance through quantitative comparisons on the Atari 100k benchmark. The code is available at https://github.com/jrobine/sgf.
Cite
Text
Robine et al. "Simple, Good, Fast: Self-Supervised World Models Free of Baggage." International Conference on Learning Representations, 2025.Markdown
[Robine et al. "Simple, Good, Fast: Self-Supervised World Models Free of Baggage." International Conference on Learning Representations, 2025.](https://mlanthology.org/iclr/2025/robine2025iclr-simple/)BibTeX
@inproceedings{robine2025iclr-simple,
title = {{Simple, Good, Fast: Self-Supervised World Models Free of Baggage}},
author = {Robine, Jan and Höftmann, Marc and Harmeling, Stefan},
booktitle = {International Conference on Learning Representations},
year = {2025},
url = {https://mlanthology.org/iclr/2025/robine2025iclr-simple/}
}