Home

About

Advanced Search

Browse by Discipline

Scientific Societies

E-print Alerts

Add E-prints

E-print Network
FAQHELPSITE MAPCONTACT US


  Advanced Search  

 
Learning and Measuring Specialization in Collaborative Swarm Systems
 

Summary: Learning and Measuring Specialization in
Collaborative Swarm Systems
Special issue on Mathematics and Algorithms of Social Interactions,
C. Anderson & T. Balch (Eds.), Adaptive Behavior, 12(34):199212, Dec. 2004.
Ling Li
Learning Systems Group, California Institute of Technology
Alcherio Martinoli
Swarm-Intelligent Systems Research Group, EPFL
Yaser S. Abu-Mostafa
Learning Systems Group, California Institute of Technology
This paper addresses qualitative and quantitative diversity and specialization issues in the framework of self-
organizing, distributed, artificial systems. Both diversity and specialization are obtained via distributed learning
from initially homogeneous swarms. While measuring diversity essentially quantifies differences among the in-
dividuals, assessing the degree of specialization implies correlation between the swarm's heterogeneity with its
overall performance. Starting from the stick-pulling experiment in collective robotics, a task that requires the
collaboration of two robots, we abstract and generalize in simulation the task constraints to k robots collabo-
rating sequentially or in parallel. We investigate quantitatively the influence of task constraints and types of
reinforcement signals on performance, diversity, and specialization in these collaborative experiments. Results
show that, though diversity is not explicitly rewarded in our learning algorithm, even in scenarios without explicit
communication among agents the swarm becomes specialized after learning. The degrees of both diversity and

  

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

 

Collections: Computer Technologies and Information Sciences