world-machine 0.2

Investigating the concept and creation of computational world models.

World Machine

World Machine is a research project that investigates the concept and creation of computational world models. These AI systems create internal representations to understand and make predictions about the external world. See the project page for more information.

This repository contains the code for the architecture and protocol we developed for this project. For information about the experiments performed, see the "experiments" directory.

This project was developed as part of the Cognitive Architectures research line from the Hub for Artificial Intelligence and Cognitive Architectures (H.IAAC) of the State University of Campinas (UNICAMP). See more projects from the group here.

Repository Structure

• src: world_machine source code.
• experiments: code for the developed experiments
• page: project page source.
• benchmark: code performance benchmark.
• ci_cd: deploy scripts.
• examples: examples of how to use World Machine.

Dependencies / Requirements

• Python >= 3.10
• Other dependencies are automatically installed with pip

Installation / Usage

• Installing using pip:

  pip install --upgrade pip
  pip install world_machine
  

• For installing from the repository:

  git clone https://github.com/H-IAAC/WorldMachine
  cd WorldMachine
  pip install --upgrade pip
  pip install .
  

See the "My First World Machine" example for how to create and train a model.

Citation

@software{my_citation,
author = {Cardoso do Nascimento, Elton and Dornhofer Paro Costa, Paula},
title = {World Machine},
url = {https://h-iaac.github.io/WorldMachine/}
}

Authors

• (2025-) Elton Cardoso do Nascimento: M. Eng. student, FEEC-UNICAMP
• (Advisor, 2025-) Paula Dornhofer Paro Costa: Professor, FEEC-UNICAMP

Acknowledgements

Project supported by the brazilian Ministry of Science, Technology and Innovations, with resources from Law No. 8,248, of October 23, 1991