World models are defined as a compressed spatial and temporal learned representation of an environment. The learned representation is typically a neural network, making transfer of the learned environment dynamics and explainability a challenge. In this paper, we propose an approach, Finite Automata Extraction (FAE), that learns a neuro-symbolic world model from gameplay video represented as programs in a novel domain-specific language (DSL): Retro Coder. Compared to prior world model approaches, FAE learns a more precise model of the environment and more general code than prior DSL-based approaches.
Cite
@article{arxiv.2508.11836,
title = {Finite Automata Extraction: Low-data World Model Learning as Programs from Gameplay Video},
author = {Dave Goel and Matthew Guzdial and Anurag Sarkar},
journal= {arXiv preprint arXiv:2508.11836},
year = {2026}
}