Advanced Search

Browse by Discipline

Scientific Societies

E-print Alerts

Add E-prints

E-print Network

  Advanced Search  

Emergent Specialization in Swarm Systems Ling Li, Alcherio Martinoli, and Yaser S. Abu-Mostafa

Summary: Emergent Specialization in Swarm Systems
Ling Li, Alcherio Martinoli, and Yaser S. Abu-Mostafa
California Institute of Technology, Pasadena, CA 91125, USA
Abstract. Distributed learning is the learning process of multiple au-
tonomous agents in a varying environment, where each agent has only
partial information about the global task. In this paper, we investigate
the influence of different reinforcement signals (local and global) and
team diversity (homogeneous and heterogeneous agents) on the learned
solutions. We compare the learned solutions with those obtained by sys-
tematic search in a simple case study in which pairs of agents have to
collaborate in order to solve the task without any explicit communica-
tion. The results show that policies which allow teammates to specialize
find an adequate diversity of the team and, in general, achieve similar
or better performances than policies which force homogeneity. However,
in this specific case study, the achieved team performances appear to be
independent of the locality or globality of the reinforcement signal.
1 Introduction
Swarms of relatively simple autonomous agents can exhibit complex behavior
which appears to transcend the individual ability of the agents. Perhaps the
most striking examples are from nature: social insect colonies are able to build


Source: Abu-Mostafa, Yaser S. - Department of Mechanical Engineering & Computer Science Department, California Institute of Technology


Collections: Computer Technologies and Information Sciences