Control of nonlinear continuous-time multi-input and multi-output dynamic systems using neuroevolution
By: Ivan Kenický, Ivan Sekaj and Filip Zúbek
References
- R. S. Sutton and A. G. Barto, Reinforcement Learning: An Introduction, 2nd ed. Cambridge, MA: MIT Press, 2018.
- V. Mnih et al., “Human-level control through deep reinforcement learning,” Nature, vol. 518, pp. 529–533, 2015.
- A. E. Eiben and J. E. Smith, Introduction to Evolutionary Computing, 1st ed. Berlin, Germany: Springer-Verlag, 2003.
- T. Bäck, Evolutionary Algorithms in Theory and Practice: Evolution Strategies, Evolutionary Programming, Genetic Algorithms, 1st ed. New York, NY, USA: Oxford University Press, 1996.
- T. Bäck, D. B. Fogel and Z. Michalewicz, eds., Handbook of Evolutionary Computation, 1st ed. Bristol, UK: Institute of Physics Publishing; New York, NY, USA: Oxford University Press, 1997.
- N. Hansen, S. D. Müller and P. Koumoutsakos, “Reducing the time complexity of the derandomized evolution strategy with covariance matrix adaptation (CMA -ES),” Evolutionary Computation, vol. 11, no. 1, pp. 1–18, 2003.
- J. H. Holland, Adaptation in Natural and Artificial Systems, 2nd ed. Cambridge, MA: MIT Press, 1992.
- Z. Michalewicz, Genetic Algorithms + Data Structures = Evolution Programs, 3rd ed. Berlin, Germany: Springer-Verlag, 1996.
- D. Floreano, P. Dürr and C. Mattiussi, “Neuroevolution: From architectures to learning,” Evolutionary Intelligence, vol. 1, no. 1, pp. 47–62, 2008.
- R. M. Khan, “A Review Study on Neuro Evolution,” International Journal of Scientific Research and Engineering Trends, vol. 7, pp. 133–137, 2021.
- R. Miikkulainen, “Neuroevolution,” in Encyclopedia of Machine Learning, C. Sammut and G. I. Webb, Eds. Boston, MA, USA: Springer, 2010.
- S. Bandyopadhyay and S. Bhasin, “Safe reinforcement learning control for continuous-time nonlinear systems without a backup controller,” arXiv preprint arXiv:2209.08922, 2022.
- Y. Huang, Y. Jia and X. Y. Zhou, “Sublinear regret for an actor-critic algorithm in continuous-time linear-quadratic reinforcement learning,” arXiv preprint arXiv:2407.17226, 2024.
- H. Wu, J. Zheng, Y.-H. Liu and D. Li, “Output-feedback control of linear continuous-time systems using discounted inverse reinforcement learning,” IEEE Transactions on Cybernetics, early access, 2026.
- Q. Meng and Y. Peng, “Output-feedback quadratic tracking control of continuous-time systems by using off-policy reinforcement learning with neural networks observer,” in Proc. IEEE Chinese Control and Decision Conf. (CCDC), Hefei, China, 2020, pp. 1–6.
- R. G. Hart, E. Griffis, O. S. Patil and W. E. Dixon, “Lyapunov-based physics-informed LSTM neural network-based adaptive control,” IEEE Control Systems Letters, vol. 8, pp. 13–18, 2024.
- “Lyapunov-based long short-term memory (Lb-LSTM) neural network-based control,” IEEE Control Systems Letters, 2023, Art. no. 3291328.
- “LSTM-MPC: A deep learning based predictive control method for multimode process control,” IEEE Transactions on Industrial Electronics, early access, 2022.
- “Fast nonlinear model predictive control using LSTM networks: A model linearisation approach,” in Proc. European Control Conference (ECC), 2022.
- “Robust offset-free constrained model predictive control with long short-term memory networks—Extended version,” arXiv preprint arXiv:2303.17304, 2023.
- F. J. Gomez and R. Miikkulainen, “Solving non-Markovian control tasks with neuroevolution,” in Proc. Int. Joint Conf. Artif. Intell. (IJCAI), San Francisco, CA, USA, 1999, pp. 1356–1361.
- P. Pagliuca, N. Milano and S. Nolfi, “Efficacy of modern neuro-evolutionary strategies for continuous control optimization,” arXiv preprint arXiv:1912.05239, 2019.
- F. J. Gomez, J. Schmidhuber and R. Miikkulainen, “Efficient nonlinear control through neuroevolution,” in Machine Learning: ECML 2006, Lecture Notes in Computer Science, vol. 4212. Berlin, Germany: Springer, 2006, pp. 64–74.
- S. C. Duong, E. Uezato, H. Kinjo and T. Yamamoto, “Intelligent control strategies for the Acrobot using neurocontroller optimized by genetic algorithm,” SICE Journal of Control, Measurement, and System Integration, vol. 2, no. 5, pp. 317–324, 2009.
- Y. Park, M. Choi and K. Y. Lee, “An optimal tracking neuro-controller for nonlinear dynamic systems,” IEEE Transactions on Neural Networks, vol. 7, no. 5, pp. 1099–1110, 1996.
- I. Sekaj, I. Kenický, F. Zúbek and J. Skirkanič, “Design of neuro-controllers for nonlinear continuous-time systems using evolutionary algorithm,” in Proc. 10th Int. Conf. Control, Decision and Information Technologies (CoDIT), Valletta, Malta, 2024, pp. 1165–1170.
- M. Le Clec’h and P. Bellec, “Neuroevolution of recurrent architectures on control tasks,” arXiv preprint arXiv:2304.12431, 2023.
- R. C. Dorf, Modern Control Systems. Reading, MA, USA: Addison-Wesley, 1990.
- B. C. Kuo, Automatic Control Systems, 6th ed. Englewood Cliffs, NJ, USA: Prentice-Hall, 1991.
- The MathWorks, Inc., MATLAB, version R2022a. Natick, MA, USA: The MathWorks, 2022.
DOI: https://doi.org/10.2478/jee-2026-0035 | Journal eISSN: 1339-309X (formerly 1335-3632) | Journal ISSN: 1335-3632
Language: English
Page range: 366 - 375
Submitted on: Jun 10, 2026
Published on: Aug 27, 2026
Published by: Slovak University of Technology in Bratislava
In partnership with: Paradigm Publishing Services
Keywords:
Related subjects:
© 2026 Ivan Kenický, Ivan Sekaj, Filip Zúbek, published by Slovak University of Technology in Bratislava
This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 License.