entropy-logo

Journal Browser

Journal Browser

Information Theory in Multi-Agent Systems: Methods and Applications

A special issue of Entropy (ISSN 1099-4300). This special issue belongs to the section "Information Theory, Probability and Statistics".

Deadline for manuscript submissions: closed (20 April 2024) | Viewed by 3319

Special Issue Editor


E-Mail Website
Guest Editor
School of Computer Science, Northwestern Polytechnical University, Xi'an 710072, China
Interests: intelligent robots; decision support systems; artificial intelligence; multi-agent systems; machine learning
Special Issues, Collections and Topics in MDPI journals

Special Issue Information

Dear Colleagues,

In recent years, research on the topic of the intelligent control and autonomous decision making of Multi-Agent System (MAS) has made a splash in the real-world in the form of autonomous driving, multi-robot collaboration, and MOBA games. Despite the great success of these emerging techniques in many AI tasks, they still suffer from several limitations, such as long horizons, sparse rewards, noisy disruptions, vulnerability to unstable environments, and the "black box" nature of DNNs, which obscures the understanding of their internal representation and decision-making processes. 

Innovative approaches such as unsupervised reinforcement learning (URL) have brought about a breakthrough in solving the aforementioned problems. In this area, the contribution of Information Theory could be highly impactful. How to deal with the mutual information objectives, state entropy, and uncertainty evaluations involved in intelligent methods are essential but difficult issues to be addressed. New emergent machine learning technologies (e.g., unsupervised reinforcement learning), information theory (e.g., maximize mutual information), variational approximation, entropy estimators, and so forth will offer us new solutions. 

This Special Issue welcomes the submission of new perspectives, theories, algorithms, and applications of multi-agent systems involving information theory on the central issues of efficiency, generalization, robustness, and interpretability. 

Prof. Dr. Haobin Shi
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. Entropy is an international peer-reviewed open access monthly 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

  • multi-agent reinforcement learning
  • unsupervised reinforcement learning
  • information theory
  • information decomposition
  • variational approximation
  • latent representation
  • maximize mutual information
  • causal reinforcement learning
  • entropy estimator
  • contrastive-like unsupervised learning
  • latent-conditioned policy
  • uncertainty estimation
  • entropy-like intrinsic reward
  • meta-reinforcement learning training
  • state entropy
  • multi-agent datasets with complex interactions and relations
  • multi-agent motion planning and decision making

Published Papers (2 papers)

Order results
Result details
Select all
Export citation of selected articles as:

Research

18 pages, 733 KiB  
Article
Complexity Reduction in Analyzing Independence between Statistical Randomness Tests Using Mutual Information
by Jorge Augusto Karell-Albo, Carlos Miguel Legón-Pérez, Raisa Socorro-Llanes, Omar Rojas and Guillermo Sosa-Gómez
Entropy 2023, 25(11), 1545; https://doi.org/10.3390/e25111545 - 15 Nov 2023
Viewed by 1428
Abstract
The advantages of using mutual information to evaluate the correlation between randomness tests have recently been demonstrated. However, it has been pointed out that the high complexity of this method limits its application in batteries with a greater number of tests. The main [...] Read more.
The advantages of using mutual information to evaluate the correlation between randomness tests have recently been demonstrated. However, it has been pointed out that the high complexity of this method limits its application in batteries with a greater number of tests. The main objective of this work is to reduce the complexity of the method based on mutual information for analyzing the independence between the statistical tests of randomness. The achieved complexity reduction is estimated theoretically and verified experimentally. A variant of the original method is proposed by modifying the step in which the significant values of the mutual information are determined. The correlation between the NIST battery tests was studied, and it was concluded that the modifications to the method do not significantly affect the ability to detect correlations. Due to the efficiency of the newly proposed method, its use is recommended to analyze other batteries of tests. Full article
(This article belongs to the Special Issue Information Theory in Multi-Agent Systems: Methods and Applications)
Show Figures

Figure 1

21 pages, 8615 KiB  
Article
Hierarchical Reinforcement Learning Framework in Geographic Coordination for Air Combat Tactical Pursuit
by Ruihai Chen, Hao Li, Guanwei Yan, Haojie Peng and Qian Zhang
Entropy 2023, 25(10), 1409; https://doi.org/10.3390/e25101409 - 1 Oct 2023
Viewed by 1035
Abstract
This paper proposes an air combat training framework based on hierarchical reinforcement learning to address the problem of non-convergence in training due to the curse of dimensionality caused by the large state space during air combat tactical pursuit. Using hierarchical reinforcement learning, three-dimensional [...] Read more.
This paper proposes an air combat training framework based on hierarchical reinforcement learning to address the problem of non-convergence in training due to the curse of dimensionality caused by the large state space during air combat tactical pursuit. Using hierarchical reinforcement learning, three-dimensional problems can be transformed into two-dimensional problems, improving training performance compared to other baselines. To further improve the overall learning performance, a meta-learning-based algorithm is established, and the corresponding reward function is designed to further improve the performance of the agent in the air combat tactical chase scenario. The results show that the proposed framework can achieve better performance than the baseline approach. Full article
(This article belongs to the Special Issue Information Theory in Multi-Agent Systems: Methods and Applications)
Show Figures

Figure 1

Back to TopTop