Advanced Reinforcement Learning in Internet of Things Networks

Dear Colleagues,

The proliferation of the Internet of Things (IoT) has revolutionised how devices, systems, and people interact. IoT networks are increasingly complex, dynamic, and heterogeneous, posing significant challenges in resource allocation, energy efficiency, security, and scalability. Reinforcement learning (RL), particularly deep RL and multi-agent RL, has emerged as a powerful tool to address these challenges, enabling intelligent decision making and adaptive control in IoT ecosystems.

This Special Issue seeks to gather innovative research and cutting-edge developments in applying RL techniques to optimise IoT networks. We invite contributions addressing theoretical advancements, novel algorithms, system architectures, and practical applications of RL in the context of IoT. Submissions focusing on interdisciplinary approaches and real-world deployments are especially encouraged.

Topics of Interest

The topics of interest include, but are not limited to, the following:

• Energy efficiency: RL-based techniques for energy harvesting, power management, and extending IoT device lifetimes;
• Network optimisation: Dynamic resource allocation, routing, and bandwidth optimisation using RL;
• Multi-agent systems: Collaborative and competitive RL for IoT devices in distributed and decentralised networks;
• Security and privacy: RL-driven solutions for intrusion detection, secure communication, and data protection in IoT networks;
• Edge Computing: RL for optimising computation offloading and workload distribution in resource-constrained environments;
• 5G and beyond: Reinforcement learning for IoT integration with 5G/6G networks, network slicing, and ultra-low-latency communications;
• Autonomous IoT management: RL approaches for self-healing, self-configuring, and self-optimising IoT networks;
• Interdisciplinary research: RL applications combining IoT with smart cities, smart healthcare, smart manufacturing, and other domains;
• Scalability and adaptability: RL algorithms designed for large-scale, highly dynamic IoT environments;
• Benchmarking and evaluation: Real-world case studies, datasets, and performance benchmarks for RL in IoT systems.;
• Physical layer: RL-based strategies for channel optimisation, interference management, and localization accuracy in IoT networks;
• Responsible AI in critical infrastructure networks: Infrastructure (e.g., healthcare, autonomous vehicles, space systems) investigating the ethical and legal implications of AI-driven systems in sectors, with an emphasis on the need for trustworthy AI;
• Resilient ML in critical infrastructure networks (e.g., healthcare, autonomous vehicles, space systems): Enhancing the resilience of critical infrastructure through the integration of AI and edge computing, aiming to improve system robustness and responsiveness;
• AI safety and robustness Exploring safety aspects of AI, including the development of methods for AI systems to behave as intended and be robust against adversarial attacks.

Dr. Saurav Sthapit
Dr. Seong Ki Yoo
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Mathematics is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2600 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

• reinforcement learning (RL)
• machine learning (ML)
• internet of things (IoT)
• resilient machine learning
• physical layer
• non-terrestrial network
• optimization
• 5G and 6G
• vehicular network