scholarly journals Application of neural ordinary differential equations to the prediction of multi-agent systems

Author(s):  
Sebastian Herzog ◽  
Florentin Wörgötter

AbstractDynamic systems are usually described by differential equations, but formulating these equations requires a high level of expertise and a detailed understanding of the observed system to be modelled. In this work, we present a data-driven approach, which tries to find a parameterization of neural differential equations system to describe the underlying dynamic of the observed data. The presented method is applied to a multi-agent system with thousand agents.

1997 ◽  
Vol 06 (01) ◽  
pp. 67-94 ◽  
Author(s):  
Frances M. T. Brazier ◽  
Barbara M. Dunin-Keplicz ◽  
Nick R. Jennings ◽  
Jan Treur

This paper discusses an example of the application of a high-level modelling framework which supports both the specification and implementation of a system's conceptual design. This framework, DESIRE (framework for DEsign and Specification of Interacting REasoning components), explicitly models the knowledge, interaction, and coordination of complex tasks and reasoning capabilities in agent systems. For the application domain addressed in this paper, an operational multi-agent system which manages an electricity transportation network for a Spanish electricity utility, a comprehensible specification is presented.


2021 ◽  
pp. 107754632110340
Author(s):  
Jia Wu ◽  
Ning Liu ◽  
Wenyan Tang

This study investigates the tracking consensus problem for a class of unknown nonlinear multi-agent systems A novel data-driven protocol for this problem is proposed by using the model-free adaptive control method To obtain faster convergence speed, one-step-ahead desired signal is introduced to construct the novel protocol Here, switching communication topology is considered, which is not required to be strongly connected all the time Through rigorous analysis, sufficient conditions are given to guarantee that the tracking errors of all agents are convergent under the novel protocol Examples are given to validate the effectiveness of results derived in this article


Author(s):  
Robert E. Smith ◽  
Claudio Bonacina

In the multi-agent system (MAS) context, the theories and practices of evolutionary computation (EC) have new implications, particularly with regard to engineering and shaping system behaviors. Thus, it is important that we consider the embodiment of EC in “real” agents, that is, agents that involve the real restrictions of time and space within MASs. In this chapter, we address these issues in three ways. First, we relate the foundations of EC theory to MAS and consider how general interactions among agents fit within this theory. Second, we introduce a platform independent agent system to assure that our EC methods work within the generic, but realistic, constraints of agents. Finally, we introduce an agent-based system of EC objects. Concluding sections discuss implications and future directions.


Author(s):  
Sofia Kouah ◽  
Djamel Eddine Saïdouni

For developing large dynamic systems in a rigorous manner, fuzzy labeled transition refinement tree (FLTRT for short) has been defined. This model provides a formal specification framework for designing such systems. In fact, it supports abstraction and enables fuzziness which allows a rigorous formal refinement process. The purpose of this paper is to illustrate the applicability of FLTRT for designing multi agent systems (MAS for short), among others collective and internal agent's behaviors. Therefore, Contract Net Protocol (CNP for short) is chosen as case study.


Sign in / Sign up

Export Citation Format

Share Document