Abstract

Multiagent systems have had a powerful impact on the real world. Many of the systems it studies air traffic, satellite coordination, rover exploration are inherently multi-objective, but they are often treated as single-objective problems within the research. A very important concept within multiagent systems is that of credit assignment: clearly quantifying an individual agent's impact on the overall system performance. In this work we extend the concept of credit assignment into multi-objective problems, broadening the traditional multiagent learning framework to account for multiple objectives. We show in two domains that by leveraging established credit assignment principles in a multi-objective setting, we can improve performance by i increasing learning speed by up to 10x ii reducing sensitivity to unmodeled disturbances by up to 98.4% and iii producing solutions that dominate all solutions discovered by a traditional team-based credit assignment schema. Our results suggest that in a multiagent multi-objective problem, proper credit assignment is as important to performance as the choice of multi-objective algorithm.


Original document

The different versions of the original document can be found in:

http://dx.doi.org/10.1007/978-3-319-13563-2_35
https://link.springer.com/chapter/10.1007/978-3-319-13563-2_35,
https://www.scipedia.com/public/Yliniemi_Tumer_2014a,
https://dblp.uni-trier.de/db/conf/seal/seal2014.html#YliniemiT14a,
https://rd.springer.com/chapter/10.1007/978-3-319-13563-2_35,
https://academic.microsoft.com/#/detail/285701945
Back to Top

Document information

Published on 01/01/2014

Volume 2014, 2014
DOI: 10.1007/978-3-319-13563-2_35
Licence: CC BY-NC-SA license

Document Score

0

Views 1
Recommendations 0

Share this document

claim authorship

Are you one of the authors of this document?