Reinforcement learning in multiagent systems: a modular fuzzy approach with internal model capabilities

Most of the methods proposed to improve the learning ability in multiagent systems are not appropriate to more complex multiagent learning problems because the state space of each learning agent grows exponentially in terms of the number of partners present in the environment. We propose a novel and robust multiagent architecture to handle these problems. The architecture is based on a learning fuzzy controller whose rule base is partitioned into several different modules. Each module deals with a particular agent in the environment and the fuzzy controller maps the input fuzzy sets to the output fuzzy sets that represent the state space of each learning module and the action space, respectively. Also, each module uses an internal model table to estimate the action of the other agents. Experimental results show the robustness and effectiveness of the proposed approach.

1. Introduction

Recently, multiagent systems have been successfully utilized in many disciplines, including reinforcement learning. An agent with its goal embedded in an environment learns how to transform one environmental state into another that contains its goal. Learning from an environment is robust because agents are directly affected by the dynamics of the environment.