CaltechAUTHORS
  A Caltech Library Service

Learning and Measuring Specialization in Collaborative Swarm Systems

Li, Ling and Martinoli, Alcherio and Abu-Mostafa, Yaser S. (2004) Learning and Measuring Specialization in Collaborative Swarm Systems. Adaptive Behavior, 12 (3-4). pp. 199-212. ISSN 1059-7123. doi:10.1177/105971230401200306. https://resolver.caltech.edu/CaltechAUTHORS:20190702-144335632

Full text is not posted in this repository. Consult Related URLs below.

Use this Persistent URL to link to this item: https://resolver.caltech.edu/CaltechAUTHORS:20190702-144335632

Abstract

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 individuals, 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 collaborating 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 specialization are affected strongly by environmental conditions and task constraints. While the specialization measure reveals characteristics related to performance and learning in a clearer way than diversity does, the latter measure appears to be less sensitive to different noise conditions and learning parameters.


Item Type:Article
Related URLs:
URLURL TypeDescription
https://doi.org/10.1177/105971230401200306DOIArticle
Additional Information:© 2004 by International Society of Adaptive Behavior. First Published December 1, 2004. We would like to thank Carl Anderson, Tucker Balch, Christopher Cianci, and the anonymous reviewers, for their valuable input and suggestions. This work has been principally supported by the Caltech Center for Neuromorphic Systems Engineering under the US NSF Cooperative Agreement EEC-9402726 and the Northrop Grumman Corporation Foundation. Alcherio Martinoli is currently sponsored by a Swiss NSF professorship.
Funders:
Funding AgencyGrant Number
NSFEEC-9402726
Northrop Grumman CorporationUNSPECIFIED
Swiss National Science Foundation (SNSF)UNSPECIFIED
Center for Neuromorphic Systems Engineering, CaltechUNSPECIFIED
Subject Keywords:collaborative swarm systems, distributed learning, specialization, diversity
Issue or Number:3-4
DOI:10.1177/105971230401200306
Record Number:CaltechAUTHORS:20190702-144335632
Persistent URL:https://resolver.caltech.edu/CaltechAUTHORS:20190702-144335632
Official Citation:Li, L., Martinoli, A., & Abu-Mostafa, Y. S. (2004). Learning and Measuring Specialization in Collaborative Swarm Systems. Adaptive Behavior, 12(3–4), 199–212. https://doi.org/10.1177/105971230401200306
Usage Policy:No commercial reproduction, distribution, display or performance rights in this work are provided.
ID Code:96894
Collection:CaltechAUTHORS
Deposited By: Tony Diaz
Deposited On:08 Jul 2019 17:12
Last Modified:16 Nov 2021 17:24

Repository Staff Only: item control page