ESTABLISHING CONSENSUS IN MULTI-AGENT SYSTEMS VIA REINFORCEMENT LEARNING TECHNIQUE

Abstract

A multi agent system(MAS) in the context of artificial intelligence refers to a system composed of multiple interacting agents, which can be entities or robots. These agents work together or compete to achieve individual or collective goals. Consensus is a decision making process that aims to achieve the agreement of the majority of entities involved, it involves collaborative efforts to reach a decision that is mutually acceptable to all involved. Rein- forcement Learning is an AI algorithm utilized with robots and autonomous vehicles to learn optimal behaviors by interacting with simulated environments, thereby facilitating safer and more efficient real world decision making. In this work, the focus is on the application of RL technique Q-learning using E-puck robots. The E-puck employs Q-learning to deter- mine the most suitable actions to take within its environment. The concept of consensus is examined within the context of multi agent systems, where E-puck robots constitute the agents. Consensus, in this scenario, pertains to the agreement reached among the E-puck agents regarding their relative positions or distances. Establishing consensus among MAS and ensuring efficient communication and coordination among E-puck robots pose significant challenges, yet achieving it holds immense potential for enhancing MAS and optimizing au- tomation and decision making processes. Using RL algorithm along with webots simulation and E-puck robots the frameworks can help different agents to navigate toward a common destination while avoiding obstacles and maintaining consensus. This approach will be ben- eficial for various sectors, including healthcare assistance, defense, warehouse management, and even agricultural automation.