Multi-Agent Reinforcement Learning Techniques for the Future beyond 5G (B5G) and 6G Wireless Networks
A special issue of Sensors (ISSN 1424-8220). This special issue belongs to the section "Intelligent Sensors".
Deadline for manuscript submissions: 20 May 2024 | Viewed by 618
Special Issue Editors
Interests: 6G; MAC; B5G; NOMA; MARL; SCMA
Special Issue Information
Dear Colleagues,
Future wireless B5G and 6G networks are represented in various deployment scenarios and innovative applications, including reconfigurable intelligent surfaces (RISs), unmanned aerial vehicle (UAV)-assisted wireless networks, multi-access edge computing (MEC), beamforming transmissions in THz networks, real-time monitoring, advanced remote control systems, and massive access in cellular IoT, among others. These scenarios involve complex optimization tasks that cannot be efficiently solved using traditional optimization techniques. To tackle these problems, machine learning (ML) and deep learning (DL) have been widely adopted. However, supervised ML and DL require the availability of a large amount of a priori labeled training and testing data, which is difficult to obtain for real-life scenarios. This has served as motivation for the adoption of reinforcement learning (RL) techniques that rely on a “trial and error” approach to overcoming the constraint of using labeled datasets.
Use of conventional single-agent RL is insufficient for dealing with the expected scenarios characterized by a considerable number of interconnected communication entities, since it learns a decision-making rule (namely, policy) for one entity without considering the coordination among the others. In this context, cooperative multi-agent reinforcement learning (MARL) algorithms represent a promising solution to provide a set of entities to learn optimal joint strategies that exploit the coordination among agents. Coordination is crucial in the expected future communication scenarios, such as for reducing collisions, mitigating/avoiding interference, balancing the traffic load, optimizing mobility, and so on.
The main purpose of this Special Issue is to invite prospective authors to submit original contributions regarding applications of MARL-based frameworks, with a specific focus on communications scenarios for wireless B5G and 6G networks.
Topics of interest include, but are not limited to, the following subjects, all within the context of MARL for wireless B5G and 6G networks.
- Multi-user MEC systems
- UAV networks
- Device-to-device (D2D) and Vehicle-to-vehicle (V2V)-enabled networks
- Beam management in mmWave/THz systems
- Massive multiple-input and multiple-output (MIMO) and cell-free massive MIMO
- Interference avoidance, management, and cancellation techniques
- Access protocol design for massive IoT networks and ultra-reliable low-latency communication (URLLC) communications
- RIS-aided wireless communications
- Integrated sensing and communication scenarios
- Industrial networks (INs)
Dr. Salvatore Riolo
Dr. Luciano Miuccio
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. Sensors 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.
Keywords
- deep reinforcement learning (DRL)
- multi-agent reinforcement learning (MARL)
- communications
- wireless networks
- ultra-reliable low-latency communications (URLLC)
- B5G/6G
- spectrum access
- reconfigurable intelligent surfaces (RIS)
- Internet of Things (IoT)
- unmanned aerial vehicle (UAV)
- device-to-device (D2D)
- vehicle-to-vehicle (V2V)
- mmWave/THz systems
