Reinforcement learning algorithm for adaptive intelligent control



  • Nguyen Van Duc Institute of Military Technical Automation, Academy of Military Science and Technology
  • Sai Van Cuong (Corresponding Author) Institute of Military Technical Automation, Academy of Military Science and Technology



AI; Reinforcement learning; Intelligent control; Data-driven control; Adaptive control; PID.


Nowadays, with the development of science and technology, control objects are increasingly complex, have high nonlinearities and large uncertainties, making traditional classic control algorithms no longer effective. That leads to the construction of unknown structures and parameters and requires advanced control techniques. To solve control problems with unknown elements in the dynamic models of the control object, the intelligent adaptive control method based on reinforcement learning algorithm is capable of automatically adjusting the parameters of the controller, proposed by the authors in this article. The effectiveness and feasibility of the proposed method are verified through practical simulation. The obtained comparative simulation results confirm that the proposed controller is robust, adaptive, and has high control performance.


[1]. Girirajkumar, S. M., Kumar, A. A., & Anantharaman, N. “Tuning of a PID controller for a real time industrial process using particle swarm optimization”. International Journal of Computer Applications, 1(7), 35-40, (2010). DOI:

[2]. Cominos P, Munro N. “Pid controllers: recent tuning methods and design to specification”. IEEE Proc D; 149(1):46–53, (2002). DOI:

[3]. Acosta GG, Mayosky MA, Catalfo JM. “An expert pid controller uses refined ziegler and nichols rules and fuzzy logic ideas”. Appl Intell; 4(1): 53–66, (1994). DOI:

[4]. Porter B, Jones AH. “Genetic tuning of digital pid controllers”. Electron Lett; 28(9): 843–4, (1992). DOI:

[5]. Acosta G, Todorovich E. “Genetic algorithms and fuzzy control: a practical synergism for industrial applications”. Comput Ind;52(2): 183–95, (2003). DOI:

[6]. Zeng G-Q, Xie X-Q, Chen M-R, Weng J. “Adaptive population extremal optimization-based pid neural network for multivariable nonlinear control systems”. Swarm Evol Comput; 44: 320–34, (2019). DOI:

[7]. Richard S. Sutton and Andrew G. Barto., “Reinforcement Learning: An Introduction”, The MIT Press Cambridge, Massachusetts London, England, (2016).

[8]. Li, Y. “Deep Reinforcement Learning: An Overview”, (2017). ArXivabs/1701.07274.

[9]. TOMIN, N., KURBATSKY, V., & GULIYEV, H. “Intelligent control of a wind turbine based on reinforcement learning”. In 2019 16th Conference on Electrical Machines, Drives and Power Systems (ELMA) (pp. 1-6). IEEE, (2019). DOI:

[10]. Fan J, Wang Z, Xie Y, Yang Z “A theoretical analysis of deep Q-learning. In: Learning for Dynamics and Control”. PMLR, pp 486–489, (2020).

[11]. Zheng, J., Kurt, M. N., & Wang, X. “Integrated actor-critic for deep reinforcement learning”. In Artificial Neural Networks and Machine Learning–ICANN 2021: 30th International Conference on Artificial Neural Networks, Bratislava, Slovakia, September 14–17, 2021, Proceedings, Part IV 30 (pp. 505-518). Springer International Publishing, (2021). DOI:

[12]. Tan, H. “Reinforcement Learning with Deep Deterministic Policy Gradient”. In 2021 International Conference on Artificial Intelligence, Big Data and Algorithms (CAIBDA) (pp. 82-85). IEEE, (2021). DOI:

[13]. Zhang F, Li J, Li Z “A td3-based multi-agent deep reinforcement learning method in mixed cooperation-competition environment”. Neurocomputing 411: 206–215, (2020). DOI:

[14]. Johnson M.A. and M.H. Moradi. “Chapter 8, in: PID Control - New Identification and Design Methods”, pp. 297-337. Springer-Verlag London Limited. ISBN-10: 1-85233-702-8, (2005).

[15]. Kwok, D.P. and P. Wang. “Fine-tuning of classical PID Controllers based on Genetic Algorithms”. IEEE Inter. Workshop on Emerging Technologies and Factory Automation, pp. 37-43, (1992). DOI:

[16]. Jones A.H. and P.B.M. Oliveira. “Genetic Auto-tuning of PID Controllers”. IEEE Conf. Publ. No. 414, 12-14 Sep 1995, pp. 141-145, (1995).



How to Cite

Nguyễn Văn Đức, and Sái Văn Cường. “Reinforcement Learning Algorithm for Adaptive Intelligent Control”. Journal of Military Science and Technology, no. CAPITI, Apr. 2024, pp. 62-68, doi:10.54939/1859-1043.j.mst.CAPITI.2024.62-68.



Research Articles