A method of the organizational structure synthesis of centralized multi-agent systems with a possibility of its automatic adaptation in the event of changing the environment parameters or the set task

Abstract

Background. The object of research is multi-agent systems. The subject of the research is the methods of synthesizing the organizational structure of a multi-agent system. The purpose of the work is to develop a method for synthesizing the organizational structure of centralized multi-agent systems with the possibility of its automatic adaptation in case of changes in environmental parameters or the task. Materials and methods. Biogeographic algorithm, reinforcement learning paradigm methods. Results. As a result, a method was developed for synthesizing the organizational structure of centralized multi-agent systems with the possibility of its automatic adaptation in the event of a change in the parameters of the environment or the task set, based on the use of a biogeographic algorithm and the reinforcement-learning paradigm. Conclusions. The developed method can find its practical application in the implementation of the following tasks: inspection (or pairing) of infrastructure objects by mobile robots; implementation of artificial intelligence in computer games.

Keywords

• multi-agent system
• organizational structure
• synthesis
• adaptation
• biogeographical algorithm
• reinforcement learning