Automatic Configuring Reinforcement Learning Powered Plug and Play Hardware System

Sharfa Nawab; Bushra Khan; Bisma Malik; Shivania; Hira Solangi

doi:10.33411/IJIST/1721

Authors

Sharfa Nawab Department of Computer Science, Quaid-e-Awam University of Engineering Science & Technology, Nawabshah, Sindh
Bushra Khan Department of Computer Science, Quaid-e-Awam University of Engineering Science & Technology, Nawabshah, Sindh
Bisma Malik Department of Computer Science, Quaid-e-Awam University of Engineering Science & Technology, Nawabshah, Sindh
Shivania Department of Computer Science, Quaid-e-Awam University of Engineering Science & Technology, Nawabshah, Sindh
Hira Solangi Department of Computer Science, Quaid-e-Awam University of Engineering Science & Technology, Nawabshah, Sindh

DOI:

https://doi.org/10.33411/IJIST/1721

Keywords:

Internet of Things (IoT), Embedded Systems, Plug-and-Play, Reinforcement Learning (RL), Automatic Automation, Real-Time Visualization, Adaptive System

Abstract

The introduction of new Internet of Things (IoT) devices in modern automation systems remains a challenge because developers must manually code, calibrate, and configure each device. each sensor and actuator require individualized programming, which contributes to longer development times and reduces the scalability and flexibility of smart systems. To overcome these constraints, the present research proposes an adaptive and self-learning control structure that allows hardware integration using Reinforcement Learning (RL) in a plug-and-play manner. The system automatically identifies, configures, and manages hardware devices via software agents, limiting the need for human intervention. The proposed system bridges the gap between hardware and software layers by integrating embedded systems, communication protocols, and RL-based adaptive control, creating an integrated system. This study enhances automation, scalability, and adaptability, enabling more efficient IoT ecosystems while significantly reducing manual effort required for programming and system calibration.

References

Bessam Abdulrazak, Suvrojoti Paul, “IoT Architecture with Plug and Play for Fast Deployment and System Reliability: AMI Platform,” Lect. Notes Comput. Sci. (including Subser. Lect. Notes Artif. Intell. Lect. Notes Bioinformatics), 2022, [Online]. Available: https://link.springer.com/chapter/10.1007/978-3-031-09593-1_4

S. V. Majid Abdolshah, Hung Le, Thommen Karimpanal George, Sunil Gupta, Santu Rana, “Plug and Play, Model-Based Reinforcement Learning,” arXiv:2108.08960, 2021, [Online]. Available: https://arxiv.org/abs/2108.08960

Alessandra Sorrentino, Filippo Cavallo, “A Plug and Play Transparent Communication Layer for Cloud Robotics Architectures,” Robotics, vol. 9, no. 1, p. 17, 2020, [Online]. Available: https://www.mdpi.com/2218-6581/9/1/17

Z. Xu, K. Wu, W. Zhang, J. Tang, Y. Wang, “PnP-DRL: A Plug-and-Play Deep Reinforcement Learning Approach for Experience-Driven Networking,” IEEE J. Sel. Areas Commun., vol. 39, no. 8, pp. 2476–2486, 2021, [Online]. Available: https://ieeexplore.ieee.org/document/9454317

F. Y. Zakaria Maamar, Mohamed Sellami, Fatma Masmoudi, Muhammad Asim, Abdul Haseeb, Thar Baker, “A Plug&Play approach for modeling and simulating applications in the era of internet of social things,” IET Smart Cities, 2021, [Online]. Available: https://ietresearch.onlinelibrary.wiley.com/doi/10.1049/smc2.12005

Kai Zhang, Yawei Li, Wangmeng Zuo, Lei Zhang, Luc Van Gool, Radu Timofte, “Plug-and-Play Image Restoration with Deep Denoiser Prior,” IEEE Trans. Pattern Anal. Mach. Intell., 2020, [Online]. Available: https://arxiv.org/abs/2008.13751

I. Al Ridhawi, S. Otoum, M. Aloqaily, and A. Boukerche, “Generalizing AI: Challenges and Opportunities for Plug and Play AI Solutions,” IEEE Netw., vol. 35, no. 1, pp. 372–379, Mar. 2021, doi: 10.1109/MNET.011.2000371.

R. G. Gavaskar, C. D. Athalye, and K. N. Chaudhury, “On Plug-and-Play Regularization Using Linear Denoisers,” IEEE Trans. Image Process., vol. 30, pp. 4802–4813, 2021, doi: 10.1109/TIP.2021.3075092.

U. S. Kamilov, C. A. Bouman, G. T. Buzzard, and B. Wohlberg, “Plug-and-Play Methods for Integrating Physical and Learned Models in Computational Imaging: Theory, algorithms, and applications,” IEEE Signal Process. Mag., vol. 40, no. 1, pp. 85–97, Jan. 2023, doi: 10.1109/MSP.2022.3199595.

Yutaka Matsuo, Yann LeCun, “Deep learning, reinforcement learning, and world models,” Neural Networks, vol. 152, pp. 267–275, 2022, [Online]. Available: https://www.sciencedirect.com/science/article/pii/S0893608022001150

C. Szepesvári, “Algorithms for Reinforcement Learning,” Springer Nat., 2010, doi: 10.1007/978-3-031-01551-9.

Chong Wang, Rongkai Zhang, Saiprasad Ravishankar, Bihan Wen, “REPNP: Plug-and-Play with Deep Reinforcement Learning Prior for Robust Image Restoration,” Proc. - Int. Conf. Image Process. ICIP, 2022, [Online]. Available: https://arxiv.org/abs/2207.12056

D. K. Denis Tarasov, Kirill Brilliantov, “Is Value Functions Estimation with Classification Plug-and-play for Offline Reinforcement Learning?,” arXiv:2406.06309, 2024, [Online]. Available: https://arxiv.org/abs/2406.06309

Jiajun Chai, Guojun Yin, Zekun Xu, Chuhuai Yue, Yi Jia, Siyu Xia, Xiaohan Wang, Jiwen Jiang, Xiaoguang Li, Chengqi Dong, Hang He, Wei Lin, “RLFactory: A Plug-and-Play Reinforcement Learning Post-Training Framework for LLM Multi-Turn Tool-Use,” arXiv:2509.06980, vol. 8, 2025, [Online]. Available: https://arxiv.org/abs/2509.06980

Michael Laskin, Kimin Lee, Adam Stooke, Lerrel Pinto, Pieter Abbeel, Aravind Srinivas, “Reinforcement Learning with Augmented Data,” Adv. Neural Inf. Process. Syst., vol. 11, 2020, [Online]. Available: https://arxiv.org/abs/2004.14990

Kaixuan Wei, Angelica Aviles-Rivero, Jingwei Liang, Ying Fu, Carola-Bibiane Schönlieb, Hua Huang, “Tuning-free Plug-and-Play Proximal Algorithm for Inverse Imaging Problems,” 37th Int. Conf. Mach. Learn. ICML, 2020, [Online]. Available: https://arxiv.org/abs/2002.09611