Tutorial: Evolution of Neural Networks

Risto Miikkulainen
Neural Networks Research Group, UT Austin
and
Cognizant AI Lab

Description

Neuroevolution, or optimization of neural networks through evolutionary computation, is a method for constructing intelligent agents through population-based search. It is particularly useful in partially observable domains with sparse and multiobjective reinforcement; compared to other policy search techniques, its power comes from extensive exploration that allows it to find effective, often surprising solutions. Prime application domains include robotic control, game-playing agents, and decision-making. More recently, it has also been extended to optimizing deep-learning architectures, understanding how biological intelligence evolved, and optimizing neural networks for hardware implementation. Several synergies have also emerged with reinforcement learning and large language models. This tutorial introduces participants to the basics of neuroevolution, progresses to several advanced topics that make neuroevolution effective and general, reviews example application areas, and proposes further research questions. An optional hands-on exercise makes these concepts concrete and allows the participants to take advantage of neuroevolution immediately.

Presentation Materials

A preliminary version: Slides (4-up pdf), video

Demos

The slides include numerous demos (i.e. animations). They don't run in the 4-up pdf, however they (and more) are included in the Neuroevolution book demo page.

Neuroevolution Exercise (Colab)

This excercise (authored by Yujin Tang) can be run as a notebook in Google Colab. There are three parts:

(1) Neuroevolution for control
(2) Evolutionary Model Merging
(3) Quality Diversity for Model Merging.

Instructions are given in the notebook.

Further Reading

Book: Neuroevolution: Harnessing Creativity in AI Model Design (MIT Press, forthcoming 2025).
A survey article in Science on neuroevolution in neuroscience.
A short summary article on neuroevolution.
A survey article in Nature Machine Intelligence.

Last modified: Sun Sep 14 20:27:27 PDT 2025