Diseño e implementación de una arquitectura multi agente para comunicar conocimientos de aprendizaje por refuerzo y mejorar el comportamiento de los agentes

Abstract

This research project presents a multi agent architecture which uses reinforcement learning. The goal is to design a system that able the agents take advantage of its peers’ knowledge. The knowledge of the environment is obtained from the reinforcement learning algorithm, Q-learning. While, the multi agent architecture sets a communication model between the agents of the system. To reach the goal, the present research project takes advantage of the Q-learning characteristic, off-policy, incorporating a condition before the use of ε-greedy. This condition allows the agents not to explore a state that has already been sent by another agent, or itself. In the proposed multi agent architecture the agents work in pairs. Each pair of agents have two different behaviors allowing them to communicate and work on relevant states of the environment. The conditions to send the states depend on the environment, specifically, it depends on the circumstances which the agent obtains a reward from the environment. The results of this work show that through the proposed architecture, the number agent-environment interactions that the agents need to improve their behavior is reduced by more than 90%.