The Emergence of Wireless MAC Protocols with Multi-Agent Reinforcement Learning

Mota, Mateus P.; Valcarce, Alvaro; Gorce, Jean-Marie; Hoydis, Jakob

doi:10.48550/arxiv.2108.07144

Cited by 7 publications

(21 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…2) Emergent Protocol Design: As explained above, the classical MAC protocol design process is limited because it is not grounded in an actual environment. To cope with such limitation, in system 1 MAC [7]- [9], the advantage for designing protocols using NN is presented. However, contrary to our endeavor to develop novel semantic communication protocols, most works on emergent communication protocol design are based on learning an NN for a given environment such as wireless MAC using MADRL [7], sensor networks, and low-earth orbit satellite networks [21], [22].…”

Section: A Related Workmentioning

confidence: 99%

“…To cope with such limitation, in system 1 MAC [7]- [9], the advantage for designing protocols using NN is presented. However, contrary to our endeavor to develop novel semantic communication protocols, most works on emergent communication protocol design are based on learning an NN for a given environment such as wireless MAC using MADRL [7], sensor networks, and low-earth orbit satellite networks [21], [22]. In addition, in [23], the authors apply NN for optimizing the MAC pipeline by selecting appropriate protocols.…”

Section: A Related Workmentioning

confidence: 99%

“…Alternatively, goal-oriented and task-specific MAC protocols have recently been proposed, wherein signaling messages emerge naturally from a given environment while conducting a downstream task [7]- [9]. For instance, with two user equipments (UEs) and a base station (BS) as visualized in Fig.…”

mentioning

confidence: 99%

“…For instance, with two user equipments (UEs) and a base station (BS) as visualized in Fig. 1, M. Mota et al [7] have shown that uplink CMs (UCMs) and downlink CMs (DCMs) in the control plane can emerge for the task of establishing collisionfree data communication in the user plane. The key idea comes from interpreting MAC protocol operations through the lens of multi-agent deep reinforcement learning (MADRL) with cheap talk communication among UE agents through the BS [10].…”

mentioning

confidence: 99%

“…The overarching goal of this paper is to fill the void between goal-oriented NPMs and generalpurpose MAC protocols. As its first step, we revisit the NPM learning scenario considered in [7], and propose a novel framework to transform the trained NPM into a semantic protocol model (SPM). This NPM-to-SPM transformation is inspired by human language [12] and logic programming language for symbolic artificial intelligence (AI) [13], as summarized next.…”

mentioning

confidence: 99%

See 4 more Smart Citations

Towards Semantic Communication Protocols: A Probabilistic Logic Perspective

Seo¹,

Park²,

Ko³

et al. 2022

Preprint

View full text Add to dashboard Cite

Classical medium access control (MAC) protocols are interpretable, yet their task-agnostic control signaling messages (CMs) are ill-suited for emerging mission-critical applications. By contrast, neural network (NN) based protocol models (NPMs) learn to generate task-specific CMs, but their rationale and impact lack interpretability. To fill this void, in this article we propose, for the first time, a semantic protocol model (SPM) constructed by transforming an NPM into an interpretable symbolic graph written in the probabilistic logic programming language (ProbLog). This transformation is viable by extracting and merging common CMs and their connections while treating the NPM as a CM generator. By extensive simulations, we corroborate that the SPM tightly approximates its original NPM while occupying only 0.02% memory. By leveraging its interpretability and memory-efficiency, we demonstrate several SPM-enabled applications such as SPM reconfiguration for collision-avoidance, as well as comparing different SPMs via semantic entropy calculation and storing multiple SPMs to cope with non-stationary environments.

show abstract

Section: A Related Workmentioning

confidence: 99%

Section: A Related Workmentioning

confidence: 99%

mentioning

confidence: 99%

mentioning

confidence: 99%

mentioning

confidence: 99%

See 3 more Smart Citations

Towards Semantic Communication Protocols: A Probabilistic Logic Perspective

Seo¹,

Park²,

Ko³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

Task-Oriented Communication Design in Cyber-Physical Systems: A Survey on Theory and Applications

Mostaani

Sharma

et al. 2022

IEEE Access

View full text Add to dashboard Cite

Communication system design has been traditionally guided by task-agnostic principles, which aim at efficiently transmitting as many correct bits as possible through a given channel. However, in the era of cyber-physical systems, the effectiveness of communications is not dictated simply by the bit rate, but most importantly by the efficient completion of the task in hand, e.g., controlling remotely a robot, automating a production line or collaboratively sensing through a drone swarm. In parallel, it is projected that by 2023, half of the worldwide network connections will be among machines rather than humans. In this context, it is crucial to establish a new paradigm for designing communication strategies for multi-agent cyber-physical systems. This is a daunting task, since it requires a combination of principles from information, communication, control theories and computer science in order to formalize a general framework for task-oriented communication designs. In this direction, this paper reviews and structures the relevant theoretical work across a wide range of scientific communities. Subsequently, it proposes a general conceptual framework for task-oriented communication design, along with its specializations according to targeted use cases. Furthermore, it provides a survey of relevant contributions in dominant applications, such as industrial internet of things, multi-unmanned aerial vehicle (UAV) systems, autonomous vehicles, distributed learning systems, smart manufacturing plants, 5G and beyond self-organizing networks, and tactile internet. Finally, this paper also highlights the most important open research topics from both the theoretical framework and application points of view.INDEX TERMS Autonomous vehicles, cyber-physical systems, federated learning, industrial IoT, reinforcement learning, task-oriented communications, goal-oriented communications, multiagent systems, multi-UAV systems, 5G self-organized networks, smart manufacturing plants, tactile internet.

show abstract

Task-Effective Compression of Observations for the Centralized Control of a Multiagent System Over Bit-Budgeted Channels

Mostaani,

Vu,

Chatzinotas

et al. 2024

IEEE Internet Things J.

View full text Add to dashboard Cite

We consider a task-effective quantization problem that arises when multiple agents are controlled via a centralized controller (CC). While agents have to communicate their observations to the CC for decision-making, the bit-budgeted communications of agent-CC links may limit the task-effectiveness of the system which is measured by the system's average sum of stage costs/rewards. As a result, each agent should compress/quantize its observation such that the average sum of stage costs/rewards of the control task is minimally impacted. We address the problem of maximizing the average sum of stage rewards by proposing two different Action-Based State Aggregation (ABSA) algorithms that carry out the indirect and joint design of control and communication policies in the multi-agent system. While the applicability of ABSA-1 is limited to single-agent systems, it provides an analytical framework that acts as a stepping stone to the design of ABSA-2. ABSA-2 carries out the joint design of control and communication for a multi-agent system. We evaluate the algorithms -with average return as the performance metric -using numerical experiments performed to solve a multi-agent geometric consensus problem. The numerical results are concluded by introducing a new metric that measures the effectiveness of communications in a multi-agent system.

show abstract

The Emergence of Wireless MAC Protocols with Multi-Agent Reinforcement Learning

Cited by 7 publications

References 12 publications

Towards Semantic Communication Protocols: A Probabilistic Logic Perspective

Towards Semantic Communication Protocols: A Probabilistic Logic Perspective

Task-Oriented Communication Design in Cyber-Physical Systems: A Survey on Theory and Applications

Task-Effective Compression of Observations for the Centralized Control of a Multiagent System Over Bit-Budgeted Channels

Contact Info

Product

Resources

About