CoSyNE C++
Released 2011
CoSyNE is a neuroevolution method where synapses of the network are evolved in separate subpopulations in a cooperative fashion. It is particularly powerful in control tasks such as double pole balancing, where it has performed better than other methods. The code is structured so that it is easy to apply it to other tasks by changing the environment class.
Download:
TAR
People
Faustino Gomez Postdoctoral Alumni tino [at] idsia ch
Publications
Neuroevolution Insights Into Biological Neural Computation 2025
Risto Miikkulainen, Science, Vol. 387 (2025), pp. eadp7478.
Neuroevolution: Harnessing Creativity in AI Agent Design 2025
Sebastian Risi, Yujin Tang, David Ha, and Risto Miikkulainen, , MIT Press, Cambridge, MA 2025. MIT Press.
Neuroevolution 2022
Risto Miikkulainen, In Encyclopedia of Machine Learning and Data Science, 3rd Edition, Dinh Phung, Claude Sammut and Geoffrey I. Webb (Eds.), New York, 2022. Springer.
Neuroevolution 2015
Risto Miikkulainen, In Encyclopedia of Machine Learning, 2nd Edition, Sammut, C. and Webb, G. I. (Eds.), Berlin, 2015. Springer.
Accelerated Neural Evolution through Cooperatively Coevolved Synapses 2008
Faustino Gomez, Juergen Schmidhuber, and Risto Miikkulainen, Journal of Machine Learning Research (2008), pp. 937-965.
Efficient Non-Linear Control through Neuroevolution 2006
Faustino Gomez, Juergen Schmidhuber, and Risto Miikkulainen, In Proceedings of the European Conference on Machine Learning, pp. 654-662, Berlin 2006. Springer.
Areas of Interest
Evolutionary Computation Neuroevolution
Labs
Neural Networks