Method for automatic reorganization of the structure of multi-agent systems, based on the application of the simulated hardening algorithm

Abstract

Background. The organizational structure of a multi-agent system includes many roles of agents, their horizontal and vertical connections, components that control their behavior, as well as rules for their functioning. The efficiency of a multi-agent system largely depends on the choice of organizational structure. During the operation of the MAS, situations are possible (for example, a significant change in environmental parameters) that require its reorganization to be performed automatically. However, existing solutions in this area have a number of significant disadvantages. The object of research is multi-agent systems. The subject of the research is methods for reorganizing the structure of a multi-agent system. The goal of the work is to develop a method for automatically reorganizing the structure of the MAS in a complex, partially observable, dynamic environment. Materials and methods. Simulated hardening algorithm, reinforcement learning paradigm methods. Results. As a result, a method was developed for automatic reorganization of the structure of multi-agent systems, initiated when environmental parameters change, based on the use of a simulated hardening algorithm and a reinforcement learning paradigm. Conclusions. The developed method can find its practical application in the implementation of the following tasks: inspection (or patrolling) of infrastructure facilities by mobile robots; implementation of artificial intelligence in computer games.

Keywords

• multi-agent system
• organizational structure
• adaptation
• simulated hardening algorithm
• reinforcement learning