Role Modeling for Adaptive Multiagent Systems Engineering

Abstract

The future of computing systems is leading to a growing complexity of heterogeneous computing systems integration situated in highly dynamic and uncertain environment. Selforganization has been proposed to be one of the solutions due to its autonomous capability to govern itself and to adapt upon changes. Developing self-organizing systems requires a suitable modeling method because of its unique characteristics, such as self-adaptive, decentralized, and emergent. Existing multiagent systems engineering methodologies lack modeling methods to design behavior adaptation for self-organizing systems. This paper proposes a role modeling method that allows designers to model how agents perform behavior adaptation at runtime by making transitions from one set of roles to another in decentralized manner. The behavior adaptation of each individual agent may eventually emerge as the adaptation of the organization. The proposed modeling method also helps designers to analyze issues that may occur because of playing multiple roles, such as role conflict, role overload, role transition oscillation, and other common issues in concurrency.

Learning to Collaborate by Grouping: A Consensus-Oriented Strategy for Multi-Agent Reinforcement Learning

“…We classify existing algorithms into three categories: (i) prior knowledge-based, (ii) role-based, and (iii) subtask-based methods. Some early methods [26,18,7,27] utilize the domain knowledge to group the agents, and are limited by human labor. To solve the issue, one line of work groups multiple agents by generating diverse roles responsible for different parts.…”