Home

Neuroevolution: Harnessing Creativity in AI Agent Design

An MIT Press Book by Sebastian Risi, Yujin Tang, David Ha, and Risto Miikkulainen

Foreword by Melanie Mitchell

The online version of the book is now freely available in an open-access HTML format. The print edition will be released later in 2026.

Access the Free Online Edition

“Covering one of the most influential developments in evolutionary computing, this book is a must read for experts in the field and newcomers alike. Its easily accessible style, combined with illustrative examples and software, provides a comprehensive overview of several decades of work that have married neural-based learning with evolutionary methods.”

-Stephanie Forrest, Professor at Arizona State University

“This book is the one and only comprehensive overview of the field of neuroevolution. It is a superb reference and will undoubtedly long serve as the definitive practical and historical introduction to evolving neural networks.”

-Ken Stanley, SVP at Lila Sciences

Neuroevolution, or optimization of neural networks through evolutionary computation, has been a growing subarea of machine learning since the 1990s. Its primary focus is on evolving neural networks for intelligent agents when the training targets are not known, and good performance requires many decisions over time, such as robotic control, game playing, 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. This book introduces students to the basics of neuroevolution, progresses to several advanced topics that make neuroevolution more effective and more general, reviews example application areas, and proposes further research questions. Hands-on experience is provided through a Python-based software platform with animations, interactive demos, exercises, and project environments.
Pictured (from left to right): Yujin Tang, Sebastian Risi, David Ha, and Risto Miikkulainen

Sebastian Risi

Sebastian Risi is a Professor at the IT University of Copenhagen where he directs the Creative AI Lab and a Research Director at modl.ai. Sebastian received his PhD from the University of Central Florida in 2012. He has won several international scientific awards, including multiple best paper awards, an ERC Consolidator Grant in 2022, the Distinguished Young Investigator in Artificial Life 2018 award, a Google Faculty Research Award in 2019, and an Amazon Research Award in 2020. His interdisciplinary work has been published in major machine learning, artificial life, and human-computer interaction conferences and has been covered by various media outlets, including Science, New Scientist, Wired, Fast Company, and The Register.

Yujin Tang

Yujin Tang is a research scientist at Sakana AI. He received an M.S in Engineering from Waseda University, (and a Ph.D. in Computer Science from The University of Tokyo). Before his current job, he worked at Google Brain and later Google DeepMind as a research engineer and a research scientist, during the time of which he published multiple evolutionary computing related papers at GECCO, NeurIPS, Artificial Life, earning best paper and best paper runner-up awards. He also developed and open-sourced EvoJAX – a toolkit for accelerated neuroevolution. His current research focuses on methods of neuroevolution in the applications of improving foundation models.

David Ha

David Ha is the Co-founder and CEO of Sakana AI, an AI Lab in Tokyo focused on advancing foundational AI models using the concepts of computational evolution. He previously worked as a Research Scientist at Google, leading the Google Brain Research team in Japan. His research interests include complex systems, self-organization, and creative applications of machine learning. He has published papers in the intersection of Deep Learning, Artificial Life, Neuroevolution and Complex Systems at NeurIPS, ICLR, ICML, GECCO, Artificial Life, Collective Intelligence. Prior to joining Google, he was a derivatives trader, serving as Managing Director and head of interest rates trading at Goldman Sachs in Japan. He obtained his undergraduate in engineering science from the University of Toronto, and a PhD from the University of Tokyo.

Risto Miikkulainen

Risto Miikkulainen is a Professor of Computer Science at the University of Texas at Austin and a VP of AI Research at the Cognizant AI Lab. He received an M.S. in Engineering from Helsinki University of Technology (now Aalto University) in 1986, and a Ph.D. in Computer Science from UCLA in 1990.  His current research focuses on methods and applications of neuroevolution, as well as neural network models of natural language processing and vision; he is an author of over 500 articles in these research areas. At the Cognizant AI Lab he is scaling up these approaches to real-world problems. Risto is an AAAI, IEEE, and INNS Fellow; his work on neuroevolution has recently been recognized with the IEEE CIS Evolutionary Computation Pioneer Award, the Gabor Award of the International Neural Network Society, and Outstanding Paper of the Decade Award of the International Society for Artificial Life.
Foreword Online Supplement Preface
1 Introduction
2 The Basics
3 The Fundamentals of Neuroevolution
4 Indirect Encodings
5 Utilizing Diversity
6 Neuroevolution of Behavior
7 Neuroevolution of Collective Systems
8 Interactive Neuroevolution
9 Open-ended Neuroevolution
10 Evolutionary Neural Architecture Search
11 Optimization of Neural Network Designs
12 Synergies with Reinforcement Learning
13 Synergies with Generative AI
14 What Neuroevolution Can Tell Us About Biological Evolution?
15 Epilogue
References Subject Index Author Index
Below are links to animations that illustrate the concepts in the book, as well as several interactive demos (labeled as such) that allow exploring those concepts through a web interface.

Chapter 2: The Basics

Chapter 3: The Fundamentals of Neuroevolution

Chaper 4: Indirect Encodings

Chapter 5: Searching for / Utilizing Diversity

Chapter 6: Neuroevolution of Behavior

Chapter 7: Neuroevolution of Collective Systems

Chapter 8: Interactive Neuroevolution

Chapter 9: Open-Ended Neuroevolution

Chapter 10: Evolutionary Neural Architecture Search

Chapter 11: Evolutionary Meta-Learning

Chapter 12: Synergies with Reinforcement Learning

Chapter 13: Synergies with Generative AI

Chapter 14: What Neuroevolution Can Tell Us About Biological Evolution

Exercises

Most of the exercises below use Google Colab, a free cloud-based service that allows you to write and run your Python code in a Jupyter notebook. This platform includes many python libraries such as Ternsorflow, Matplotlib, Pandas, etc. Colab also provides access to limited GPU resources so you can run your experiments right there. You can access Colab through your Google drive. Create a copy of the exercise notebook in your Google Colab account. It has a code for the general setup; the exercise consists of filling in the missing parts of the code yourself, running it, and verifying that it works. As an example of working code, here’s the Bipedal walker example used in Chapters 2 & 3.

Assignments

Chapter 2 –
  • Evolution strategies (ES) and genetic algorithms (GA) on black-box optimization using Numpy Notebook
Chapter 3 –
  • Part 1: ES/GA evolving a neural network for the MNIST task Notebook
  • Part 2: ES/GA evolving a neural network for the CartPole task Notebook
  • Part 3: Implementing NEAT for data classification task Notebook
Chapter 4 –
  • Part 1: Evolving a CPPN for creative pattern generation Notebook
  • Part 2: Implementing MAP-Elites for MNIST Notebook
Chapter 6 – Chapter 7 –
  • Evolving Neural Cellular Automata (NCA) to generate a pattern Notebook
Chapter 8 –
  • Part 1: Neuroevolution of a simple SlimeVolley player against a random opponent Assignment
  • Part 2: Neuroevolution of a better SlimeVolley player with evolutionary arms race Assignment Notebook (for both Part1 and Part2)
  • This assignment can be run as a class-wide tournament
Chapter 12 – Tutorial Exercises –
  • This is the exercise used in some of the neuroevolution conference tutorials. It includes: pole-balancing, model merging, and MAP-Elites. Notebook

Solutions

The solutions are provided in the For Instructors page. It is password-protected; if you are an instructor or TA, please send an email to sebr@itu.dk and yujintang@sakana.ai to get it.

Course

An advanced undergraduate course based on the book was taught by Risto in Fall 2024. All the public materials for it (syllabus, reading, slides-4up, lecture recordings, exercises) are available at the course website. The Overleaf sources for the class slides and the solutions for the exercises are available upon request at the “For Instructors” page.

Tutorials

Past:
  • GECCO 2024 (pre-book: slides, video)
  • Artificial Life conference 2024 (updated for Alife 2025)
  • IJCNN 2025 (updated for AAAI 2026)
  • GECCO 2025 (updated for AAAI 2026)
  • IJCAI 2025 (updated for AAAI 2026)
  • Artificial Life conference 2025 (slides)
Coming up:
To access the materials, please click here and enter your password.  

Risi, S., Tang, Y., Ha, D., and Miikkulainen, R. (2025). Neuroevolution: Harnessing Creativity in AI Agent Design. Cambridge, MA: MIT Press. https://neuroevolutionbook.com .

BibTeX

@book{risi-et-al:book2025,
  title     = {Neuroevolution: Harnessing Creativity in AI Agent Design},
  author    = {Sebastian Risi and Yujin Tang and David Ha and Risto Miikkulainen},
  publisher = {MIT Press},
  address   = {Cambridge, MA},
  url       = {https://neuroevolutionbook.com},
  year      = {2025}
}