Full Text:   <385>

Suppl. Mater.: 

CLC number: 

On-line Access: 2022-07-21

Received: 2022-07-21

Revision Accepted: 2022-07-21

Crosschecked: 2022-07-21

Cited: 0

Clicked: 236

Citations:  Bibtex RefMan EndNote GB/T7714

-   Go to

Article info.
Open peer comments

Frontiers of Information Technology & Electronic Engineering  2022 Vol.23 No.7 P.991-994

http://doi.org/10.1631/FITEE.2240000


Institutionalized and systematized gaming for multi-agent systems


Author(s):  Jun LU, Fei-Yue WANG, Qi DONG, Qinglai WEI

Affiliation(s):  China Academy of Electronics and Information Technology, Beijing100049, China; more

Corresponding email(s):   feiyue.wang@ia.ac.cn, dongqiouc@126.com

Key Words: 


Share this article to: More |Next Article >>>

Jun LU, Fei-Yue WANG, Qi DONG, Qinglai WEI. Institutionalized and systematized gaming for multi-agent systems[J]. Frontiers of Information Technology & Electronic Engineering, 2022, 23(7): 991-994.

@article{title="Institutionalized and systematized gaming for multi-agent systems",
author="Jun LU, Fei-Yue WANG, Qi DONG, Qinglai WEI",
journal="Frontiers of Information Technology & Electronic Engineering",
volume="23",
number="7",
pages="991-994",
year="2022",
publisher="Zhejiang University Press & Springer",
doi="10.1631/FITEE.2240000"
}

%0 Journal Article
%T Institutionalized and systematized gaming for multi-agent systems
%A Jun LU
%A Fei-Yue WANG
%A Qi DONG
%A Qinglai WEI
%J Frontiers of Information Technology & Electronic Engineering
%V 23
%N 7
%P 991-994
%@ 2095-9184
%D 2022
%I Zhejiang University Press & Springer
%DOI 10.1631/FITEE.2240000

TY - JOUR
T1 - Institutionalized and systematized gaming for multi-agent systems
A1 - Jun LU
A1 - Fei-Yue WANG
A1 - Qi DONG
A1 - Qinglai WEI
J0 - Frontiers of Information Technology & Electronic Engineering
VL - 23
IS - 7
SP - 991
EP - 994
%@ 2095-9184
Y1 - 2022
PB - Zhejiang University Press & Springer
ER -
DOI - 10.1631/FITEE.2240000


Abstract: 

Multi-agent system gaming (MASG) is widely applied in military intelligence, information networks, unmanned systems, intelligent transportation, and smart grids, exhibiting systematic and organizational characteristics. It requires the multi-agent system perceive and act in a complex dynamic environment and at the same time achieve a balance between individual interests and the maximization of group interests within the system. Some problems include complex system structure, uncertain game environment, incomplete decision information, and unexplainable results. As a result, the study of multi-agent game has transformed from a traditional simple game to a game facing a high-dimensional, continuous, and complex environment, which prompts an urgent need for institutionalized and systematized gaming (InSys gaming). With this background, several important tendencies have emerged in the development of InSys gaming for multi-agent systems:

1. Analyzing the evolution law of MASG and establishing the InSys gaming theory model for multi-agent systems

The organized and systematic MASG has orderly and structured characteristics, so it is necessary to establish a system game model. To study political, military, economic, and other systemic confrontation gaming problems, the first step is to analyze the system’s internal evolution characteristics and external interaction information. In addition, establishing the evolution model of InSys gaming and studying the elements, relationships, and criteria of the game evolution help provide theoretical support for the system design, decision-making planning, and other research in this field.

2. Combining several artificial intelligence learning algorithms to achieve collaborative decision-making of multi-agent systems

The current mainstream artificial intelligence learning methods all have application advantages in specific scenarios. In solving InSys gaming problems, we can combine the environmental representation ability of deep learning and the decision generation ability of reinforcement learning (RL). For example, by building a digital simulation training environment, intelligent decision algorithms and unsupervised training methods can be designed to generate a multi-agent system’s collaborative decision in a complex and unknown environment.

3. Adopting a hierarchical task planning and decision-making action architecture to reduce the complexity of collaborative decision-making algorithms

With the increase of the scale of multi-agent systems, the problems of node coupling, observation uncertainty, and interaction disorder faced by collaborative decision-making have become increasingly prominent. The complexity of solving its systematic and organized game problems has increased significantly. A multi-agent hierarchical algorithm architecture is constructed through game task decomposition, longterm planning, and real-time action decision-making. It can effectively reduce the complexity of the search process of a collaborative decision-making algorithm. In addition, it is a feasible idea for solving an organized and systematic game.

4. Establishing the robustness analysis framework of the algorithm model to solve the model deviation between data-driven methods and the actual scene

When the training data deviates from the actual scene for data-driven methods, the algorithm’s performance will be degraded. Thus, it is necessary to study the robustness analysis framework of data-driven methods. For example, a robust algorithm model and an actual data fine-tuning method are designed to reduce the performance loss of the trained algorithm. This strategy helps support the actual deployment of data-driven methods.

Game theory has become a basic analytical framework for solving problems in strategic politics, military confrontation, market economy, and so on. The object of analysis is characterized by complex systematization and organization and has been highly concerned with and valued by academic and industrial circles alike. A multi-agent system is used to model the organized and systematic game, combined with an artificial intelligence method to solve the game decision-making problem, providing a new idea for developing theories, methods, and technologies in this field.

Darkslateblue:Affiliate; Royal Blue:Author; Turquoise:Article

Open peer comments: Debate/Discuss/Question/Opinion

<1>

Please provide your name, email address and a comment





Journal of Zhejiang University-SCIENCE, 38 Zheda Road, Hangzhou 310027, China
Tel: +86-571-87952783; E-mail: cjzhang@zju.edu.cn
Copyright © 2000 - 2022 Journal of Zhejiang University-SCIENCE