GEGELATI

GEGELATI [dʒedʒelati] is a fresh open-source reinforcement learning framework for training artificial intelligence based on Tangled Program Graphs (TPGs). The purpose of this framework, developed as a C++ shared library, is to make it as easy and as fast as possible and to train an agent on a new learning environment. The C++ library is developed to be portable, fully documented, and thoroughly unit tested to ensure its maintainability. GEGELATI is developed at the Institut d’Electronique et des Technologies du numéRique (IETR).

Recent posts

GEGELATI v1.4.0 - Erbaba Cedrina flavor

Version 1.4.0 of Gegelati was released today, with a few changes and bug fixes. This is most likely the last minor evolution before big changes coming for Ge...

Accepted Paper at ECTA2024

Quentin Vacher’s first paper has been accepted at the 16th International Conference on Evolutionary Computation Theory and Applications (ECTA).

Foutics PhD start

With the start of Paul Allaire and Quentin Vacher today, the Foutics project is getting closer to reality. Stay tuned for the first contributions!