Learning-based Physical Layer Communications for Multiagent Collaboration

Mostaani, Arsham; Simeone, Osvaldo; Chatzinotas, Symeon; Ottersten, Björn

doi:10.1109/pimrc.2019.8904190

Cited by 24 publications

(54 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this section, we evaluate our proposed schemes via numerical results for the popular rendezvous problem, in which the inter-agent communication channel is set to have a limited rate. To find the details of the rendezvous problem, please refer to [9]. The system operates in discrete time, with agents taking actions and communicating in each time step t = 1, 2, ... .…”

Section: Numerical Resultsmentioning

confidence: 99%

“…The initial state s(1) ∈ S is randomly selected by the environment. To make the problem more concrete, here we assume the presence of an instantaneous communication between agents [9]. Fig.…”

Section: A Problem Statementmentioning

confidence: 99%

“…The given examples fall in the general category of multiagent reinforcement learning, which is used in the literature as an effective framework to develop coordinated policies [5]- [9]. The distributed decision-making of multi-agent systems has been addressed in [5], [6], while many other works are focused on multi-agent (MA) communications to enhance the joint action selection in partially observed environments [7]- [10].…”

Section: Introductionmentioning

confidence: 99%

“…Deep reinforcement learning with communication of the gradients of the agents' objective function is proposed in [8] to learn the communication among multiple agents. In contrast to the above mentioned works, the impact of channel noise in the inter-agent communications is studied by [9] and the absence of dedicated communication channels by [11].…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

State Aggregation for Multiagent Communication over Rate-Limited Channels

Mostaani

Chatzinotas

et al. 2020

GLOBECOM 2020 - 2020 IEEE Global Communications Conference

Self Cite

View full text Add to dashboard Cite

A collaborative task is assigned to a multiagent system (MAS) in which agents are allowed to communicate. The MAS runs over an underlying Markov decision process and its task is to maximize the averaged sum of discounted one-stage rewards. Although knowing the global state of the environment is necessary for the optimal action selection of the MAS, agents are limited to individual observations. The inter-agent communication can tackle the issue of local observability, however, the limited rate of the inter-agent communication prevents the agent from acquiring the precise global state information. To overcome this challenge, agents need to communicate their observations in a compact way such that the MAS compromises the minimum possible sum of rewards. We show that this problem is equivalent to a form of rate-distortion problem which we call the task-based information compression. State Aggregation for Information Compression (SAIC) is introduced here to perform the task-based information compression. The SAIC is shown, conditionally, to be capable of achieving the optimal performance in terms of the attained sum of discounted rewards. The proposed algorithm is applied to a rendezvous problem and its performance is compared with two benchmarks; (i) conventional source coding algorithms and the (ii) centralized multiagent control using reinforcement learning. Numerical experiments confirm the superiority and fast convergence of the proposed SAIC.

show abstract

Section: Numerical Resultsmentioning

confidence: 99%

Section: A Problem Statementmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

State Aggregation for Multiagent Communication over Rate-Limited Channels

Mostaani

Chatzinotas

et al. 2020

GLOBECOM 2020 - 2020 IEEE Global Communications Conference

Self Cite

View full text Add to dashboard Cite

show abstract

“…In [12], [13], cooperative MARL is used to emerge a coding scheme by joint learning of communication and cooperation to solve a task with the help of a noisy communication channel. The proposition of both works is to emerge a coding scheme that is tailored to the application.…”

Section: Related Workmentioning

confidence: 99%

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

Mota,

Valcarce,

Gorce

et al. 2021

Preprint

View full text Add to dashboard Cite

In this paper, we propose a new framework, exploiting the multi-agent deep deterministic policy gradient (MAD-DPG) algorithm, to enable a base station (BS) and user equipment (UE) to come up with a medium access control (MAC) protocol in a multiple access scenario. In this framework, the BS and UEs are reinforcement learning (RL) agents that need to learn to cooperate in order to deliver data. The network nodes can exchange control messages to collaborate and deliver data across the network, but without any prior agreement on the meaning of the control messages. In such a framework, the agents have to learn not only the channel access policy, but also the signaling policy. The collaboration between agents is shown to be important, by comparing the proposed algorithm to ablated versions where either the communication between agents or the central critic is removed. The comparison with a contentionfree baseline shows that our framework achieves a superior performance in terms of goodput and can effectively be used to learn a new protocol.

show abstract

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

Mostaani

Sharma

et al. 2022

IEEE Access

Self Cite

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

Learning-based Physical Layer Communications for Multiagent Collaboration

Cited by 24 publications

References 9 publications

State Aggregation for Multiagent Communication over Rate-Limited Channels

State Aggregation for Multiagent Communication over Rate-Limited Channels

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

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

Contact Info

Product

Resources

About