# Finite Automata Extraction: Low-data World Model Learning as Programs from Gameplay Video

arXiv: https://arxiv.org/abs/2508.11836 · HTML: https://mlsanity.com/paper/2508.11836/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Video-generation world models and simulators, one of 11 directions in World models.
- Builds on 14 of its 24 references that are in the map.
- First posted on arXiv 15 Aug 2025.

## Placed in

- World models / [Video-generation world models and simulators](https://mlsanity.com/wm/video-generation-world-models-and-simulators/)

## Builds on (most cited first, 14 of 14)

- [World Models](https://mlsanity.com/paper/1803.10122/) (2018)
- [Diffusion Models Are Real-Time Game Engines](https://mlsanity.com/paper/2408.14837/) (2024)
- [DreamCoder: Growing generalizable, interpretable knowledge with wake-sleep Bayesian program learning](https://mlsanity.com/paper/2006.08381/) (2020)
- [DeepCoder: Learning to Write Programs](https://mlsanity.com/paper/1611.01989/) (2016)
- [iVideoGPT: Interactive VideoGPTs are Scalable World Models](https://mlsanity.com/paper/2405.15223/) (2024)
- [RobustFill: Neural Program Learning under Noisy I/O](https://mlsanity.com/paper/1703.07469/) (2017)
- [Analysis of Explainers of Black Box Deep Neural Networks for Computer Vision: A Survey](https://mlsanity.com/paper/1911.12116/) (2019)
- [Learning to Simulate Dynamic Environments with GameGAN](https://mlsanity.com/paper/2005.12126/) (2020)
- [Playable Video Generation](https://mlsanity.com/paper/2101.12195/) (2021)
- [MarioNette: Self-Supervised Sprite Learning](https://mlsanity.com/paper/2104.14553/) (2021)
- [Few-Shot Bayesian Imitation Learning with Logical Program Policies](https://mlsanity.com/paper/1904.06317/) (2019)
- [Learning of Generalizable and Interpretable Knowledge in Grid-Based Reinforcement Learning Environments](https://mlsanity.com/paper/2309.03651/) (2023)
- [Mechanics Automatically Recognized via Interactive Observation: Jumping](https://mlsanity.com/paper/1707.03865/) (2017)
- [KnowPC: Knowledge-Driven Programmatic Reinforcement Learning for Zero-shot Coordination](https://mlsanity.com/paper/2408.04336/) (2024)

## Abstract (arXiv)

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.