Discovering Sensing Capability in Multi-agent Systems

Abstract

Which should the sensing capabilities of agents in a Multiagent System be to solve a problem efficiently, fast and with low cost? This question often appears when trying to solve a problem using Multiagent System. This paper introduces a method to find out these sensing capabilities in order to solve a given problem. To achieve this, the sensing capability of an agent is modeled by a parametrized function and then Genetic Algorithms are used to find the parameters values. The individual behavior of the agents are found with Reinforcement Learning.