REINFORCEMENT LEARNING-BASED OPTIMIZATION TECHNIQUES FOR DYNAMIC SYSTEMS

International Journal of Computer Science (IJCS) Published by SK Research Group of Companies (SKRGC)

Abstract

Dynamic systems are widely used in industrial automation, robotics, transportation, energy management, finance, healthcare, and communication networks. Traditional optimization methods often struggle to handle uncertainties, nonlinearities, and changing environmental conditions in real time. Reinforcement Learning (RL), a branch of machine learning, has emerged as a powerful optimization framework capable of learning optimal control strategies through interaction with the environment. This paper presents a comprehensive study of reinforcement learning-based optimization techniques for dynamic systems. The study discusses RL fundamentals, system modeling approaches, optimization algorithms, and practical applications in engineering and intelligent systems. Furthermore, the paper analyzes advantages, limitations, and future research directions for RL-driven optimization. Experimental comparisons demonstrate the effectiveness of deep reinforcement learning methods over conventional optimization techniques in dynamic and uncertain environments.

References

1. R. S. Sutton and A. G. Barto, Reinforcement Learning: An Introduction, 2nd ed. Cambridge, MA, USA: MIT Press, 2018.
2. V. Mnih et al., “Human-level control through deep reinforcement learning,” Nature, vol. 518, no. 7540, pp. 529–533, 2015.
3. D. Silver et al., “Mastering the game of Go with deep neural networks and tree search,” Nature, vol. 529, no. 7587, pp. 484–489, 2016.
4. J. Schulman et al., “Proximal policy optimization algorithms,” arXiv preprint arXiv: 1707.06347, 2017.
5. Y. LeCun, Y. Bengio, and G. Hinton, “Deep learning,” Nature, vol. 521, no. 7553, pp. 436–444, 2015.
6. K. Arulkumaran et al., “Deep reinforcement learning: A brief survey,” IEEE Signal Processing Magazine, vol. 34, no. 6, pp. 26–38, 2017.
7.  M. Glavic, “Reinforcement learning for electric power system decision and control,” Electric Power Systems Research, vol. 182, 2020.
8. S. Levine et al., “End-to-end training of deep visuomotor policies,” Journal of Machine Learning Research, vol. 17, no. 39, pp. 1–40, 2016.
9. F. L. Lewis and D. Vrabie, “Reinforcement learning and adaptive dynamic programming for feedback control,” IEEE Circuits and Systems Magazine, vol. 9, no. 3, pp. 32–50, 2009.
10. B. Kiumarsi et al., “Optimal and autonomous control using reinforcement learning: A survey,” IEEE Transactions on Neural Networks and Learning Systems, vol. 29, no. 6, pp. 2042–2062, 2018.

 

Keywords

Reinforcement Learning, Dynamic Systems, Optimization, Deep Q-Network, Policy Gradient, Robotics, Smart Grid, Intelligent Control.