Machine Learning for Multi-agent Systems

Dear Colleagues,

This Special Issue, titled “Machine Learning for Multi-Agent Systems”, navigates both cooperative and competitive dynamics among agents. It explores machine learning techniques to facilitate collaborative behaviors while also refining competitive strategies within these systems. Researchers develop machine learning models that foster cooperative interactions among agents, promoting collaboration and information sharing. Simultaneously, there is a focus on leveraging deep learning to enhance competitive aspects, refining adversarial training methods and game-theoretic approaches.  

This Special Issue provides a platform for innovative ideas and best practices in Multi-Agent Systems based on machine learning. The topics span various aspects of Multi-Agent Systems, ranging from learning algorithms and architectures to communication strategies, offering rich avenues for research and advancement.

In this Special Issue, original research articles and reviews are welcome. Research areas may include (but are not limited to) the following:

• Decentralized Learning Algorithms.
• Multi-Agent Reinforcement Learning.
• Adversarial Training in Multi-Agent Systems.
• Collaborative Deep Learning Architectures.
• Communication Strategies among Agents.
• Evolutionary Game Theory in Multi-Agent Systems.
• Self-Organization in Multi-Agent Systems.
• Hierarchical Multi-Agent Systems.
• Transfer Learning in Multi-Agent Environments.

Prof. Dr. Liangjun Ke
Guest Editor

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. Electronics 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 2400 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.

• multi-agent systems
• machine learning
• decentralized learning
• multi-agent reinforcement learning
• communication