Mixed Cooperative-Competitive Communication Using Multi-agent Reinforcement Learning

Vanneste, Astrid; Wijnsberghe, Wesley Van; Vanneste, Simon; Mets, Kevin; Mercelis, Siegfried; Latré, Steven; Hellinckx, Peter

doi:10.1007/978-3-030-89899-1_20

Cited by 5 publications

(3 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The purpose is to support the sharing and reusing of knowledge and information in a distributed, heterogeneous, dynamic, and many autonomous nodes (agents) environment. At present, it has become the de facto standard of agent communication language [ 29 ].…”

Section: Methodsmentioning

confidence: 99%

Enterprise negotiation and communication management system under the guidance of the Internet of Things

2023

PLoS ONE

View full text Add to dashboard Cite

The multi-agent system is used to study the negotiation problem of virtual enterprises in the context of the Internet of Things (IoT) to strengthen the decision-making ability of enterprises and improve the negotiation efficiency between different enterprises. Firstly, virtual enterprises and high-tech virtual enterprises are introduced. Secondly, the virtual enterprise negotiation model is implemented using the agent technology in the IoT, including constructing the operation mode of the alliance enterprise agent and the member enterprise agent. Finally, a negotiation algorithm based on improved Bayesian theory is proposed. It is applied to virtual enterprise negotiation, and the effect of the negotiation algorithm is verified by setting an example. The results show that: (1) When one side of the enterprise adopts a risk-taking strategy, the number of negotiation rounds between the two sides increases. (2) High joint utility can be achieved when both parties to the negotiation adopt a conservative strategy. (3) The improved Bayesian algorithm can improve the negotiation efficiency of enterprises by reducing the number of negotiation rounds. This study aims to achieve efficient negotiation between the alliance and the member enterprises to improve the decision-making ability of the alliance owner enterprise.

show abstract

Section: Methodsmentioning

confidence: 99%

Enterprise negotiation and communication management system under the guidance of the Internet of Things

2023

PLoS ONE

View full text Add to dashboard Cite

show abstract

“…Many studies in the emergent communication field (Lazaridou, Potapenko, and Tieleman 2020) use RL and variants of the REINFORCE algorithm (Williams 1992) for solving the referential game (Foerster et al 2016;Lazaridou, Peysakhovich, and Baroni 2016;Chaabouni et al 2021). Vanneste et al (2022) provide a comprehensive review of the various ways to overcome the discretization issue within multi-agent environments. Notably, they find that none of the surveyed methods is best in all environments, and that the optimal discretization method greatly depends on the environment.…”

Section: Multi-agent Reinforcement Learningmentioning

confidence: 99%

“…A key aspect in emergent communication systems is the channel by which agents communicate when trying to accomplish a common task. Prior work has recognized the importance of communicating over a discrete channel (Havrylov and Titov 2017;Lazaridou and Baroni 2020;Vanneste et al 2022). From a scientific point of view, investigating the characteristics of communication that emerges among artificial agents may contribute to our understanding of human language evolution.…”

Section: Introductionmentioning

confidence: 99%

Emergent Quantized Communication

Carmeli

Meir

Belinkov

2023

AAAI

View full text Add to dashboard Cite

The field of emergent communication aims to understand the characteristics of communication as it emerges from artificial agents solving tasks that require information exchange. Communication with discrete messages is considered a desired characteristic, for scientific and applied reasons. However, training a multi-agent system with discrete communication is not straightforward, requiring either reinforcement learning algorithms or relaxing the discreteness requirement via a continuous approximation such as the Gumbel-softmax. Both these solutions result in poor performance compared to fully continuous communication. In this work, we propose an alternative approach to achieve discrete communication -- quantization of communicated message. Using message quantization allows us to train the model end-to-end, achieving superior performance in multiple setups. Moreover, quantization is a natural framework that runs the gamut from continuous to discrete communication. Thus, it sets the ground for a broader view of multi-agent communication in the deep learning era.

show abstract

A Review of Multi-Agent Collaborative Control

He,

Ma,

et al. 2023

2023 2nd International Conference on Artificial Intelligence, Human-Computer Interaction and Robotics (AIHCIR)

View full text Add to dashboard Cite

Mixed Cooperative-Competitive Communication Using Multi-agent Reinforcement Learning

Cited by 5 publications

References 7 publications

Enterprise negotiation and communication management system under the guidance of the Internet of Things

Enterprise negotiation and communication management system under the guidance of the Internet of Things

Emergent Quantized Communication

A Review of Multi-Agent Collaborative Control

Contact Info

Product

Resources

About