"Advanced Reinforcement Learning Approaches for Intelligent Decision-Making Systems"
Article Sidebar
Main Article Content
Reinforcement Learning (RL) has become an important branch of artificial intelligence for solving sequential decision-making problems in uncertain and changing environments. Unlike supervised learning, RL allows an agent to learn optimal actions through interaction with its surroundings by maximizing long-term rewards. Recent progress in deep learning, computing power, and data availability has significantly expanded the use of RL in healthcare, robotics, finance, transportation, and smart systems. This paper presents a structured review of RL for intelligent decision-making, covering theoretical foundations, modern algorithms, methodologies, applications, benefits, and future opportunities. Special attention is given to safe RL, explainable RL, multi-agent systems, and real-time adaptive intelligence. The study concludes that RL is expected to play a major role in next-generation autonomous and human-centered AI systems.
Downloads
References
R. S. Sutton and A. G. Barto, Reinforcement Learning: An Introduction, 2nd ed. Cambridge, MA, USA: MIT Press, 2018.
D. Silver et al., “Foundations of reinforcement learning and decision systems,” arXiv preprint arXiv:2305.04567, 2023.
Y. Zhang et al., “Safe and robust reinforcement learning for autonomous systems,” IEEE Transactions on Neural Networks and Learning Systems, vol. 35, no. 4, pp. 1234–1248, 2024.
R. Kumar and H. Lee, “Explainable decision-making in healthcare using deep reinforcement learning,” Springer Journal of Artificial Intelligence, vol. 12, no. 2, pp. 89–105, 2024.
M. Chen et al., “Multi-agent reinforcement learning for distributed decision-making under uncertainty,” ACM Transactions on Autonomous Systems, vol. 5, no. 1, pp. 1–20, 2025.
S. Li and J. Wang, “Human-in-the-loop reinforcement learning for decision support systems,” ACM Transactions on Interactive Intelligent Systems, vol. 15, no. 1, pp. 45–62, 2025.
Gupta et al., “Sample-efficient deep reinforcement learning for real-time robotics applications,” Robotics and Autonomous Systems, vol. 172, pp. 104–118, 2024.
R. Ahmed and J. Kim, “Reinforcement learning for financial decision-making under uncertainty,” IEEE Access, vol. 13, pp. 56789–56805, 2025.
L. Torres and A. Singh, “Neuro-symbolic reinforcement learning for transparent decision-making,” in Proc. AAAI Conf. Artificial Intelligence, 2023, pp. 1123–1130.
M. Fernandez and T. Zhao, “Ethical challenges in reinforcement learning systems,” AI and Ethics, vol. 3, no. 2, pp. 211–225, 2023.
V. Mnih et al., “Human-level control through deep reinforcement learning,” Nature, vol. 518, pp. 529–533, 2015.
J. Schulman et al., “Proximal policy optimization algorithms,” arXiv preprint arXiv:1707.06347, 2017.
T. Lillicrap et al., “Continuous control with deep reinforcement learning,” arXiv preprint arXiv:1509.02971, 2015.
H. Van Hasselt, A. Guez, and D. Silver, “Deep reinforcement learning with double Q-learning,” in Proc. AAAI Conf. Artificial Intelligence, 2016, pp. 2094–2100.
R. S. Sutton et al., “Policy gradient methods for reinforcement learning with function approximation,” in Advances in Neural Information Processing Systems (NeurIPS), 2000, pp. 1057–1063.
M. L. Puterman, Markov Decision Processes: Discrete Stochastic Dynamic Programming. New York, NY, USA: Wiley, 1994.
C. J. C. H. Watkins and P. Dayan, “Q-learning,” Machine Learning, vol. 8, no. 3–4, pp. 279–292, 1992.
K. Arulkumaran et al., “A brief survey of deep reinforcement learning,” IEEE Signal Processing Magazine, vol. 34, no. 6, pp. 26–38, 2017.
P. Konda and J. Tsitsiklis, “Actor-critic algorithms,” in Advances in Neural Information Processing Systems (NeurIPS), 2000, pp. 1008–1014.
M. Tan, “Multi-agent reinforcement learning: Independent vs. cooperative agents,” in Proc. Int. Conf. Machine Learning (ICML), 1993, pp. 330–337.
This work is licensed under a Creative Commons Attribution 4.0 International License.
All articles published in our journal are licensed under CC-BY 4.0, which permits authors to retain copyright of their work. This license allows for unrestricted use, sharing, and reproduction of the articles, provided that proper credit is given to the original authors and the source.