Learning from multiple sources

Abstract

This work aims at defining and testing a set of techniques that enables agents to use information from several sources during learning. In Multiagent Systems (MAS) it is frequent that several agents need to learn similar concepts in parallel. In this type of environment there are more possibilities for learning than in classical Machine Learning. Exchange of information between teams of agents that are attempting to solve similar problems may increase accuracy and learning speed at the expense of communication. One of the most interesting possibilities to explore is when the agents may have different structures and learning algorithms, thus providing different perspectives on the problems they are facing. In this paper the authors report the results of experiments made in a traffic control simulation with and without exchanging information between learning agents.