The power of teams that disagree : team formation in large action spaces

Soriano Marcolino, Leandro and Xu, Haifeng and Xin Jiang, Albert and Tambe, Milind and Bowring, Emma (2015) The power of teams that disagree : team formation in large action spaces. In: Coordination, Organizations, Institutions and Norms in Agent Systems X : COIN 2014 International Workshops, COIN@AAMAS, Paris, France, May 6, 2014, COIN@PRICAI, Gold Coast, QLD, Australia, December 4, 2014, Revised Selected Papers. Lecture Notes in Computer Science . Springer, pp. 213-232. ISBN 9783319254197

[thumbnail of coin2014Book]
Preview
PDF (coin2014Book)
coin2014Book.pdf - Accepted Version

Download (3MB)

Abstract

Recent work has shown that diverse teams can outperform a uniform team made of copies of the best agent. However, there are fundamental questions that were never asked before. When should we use diverse or uniform teams? How does the performance change as the action space or the teams get larger? Hence, we present a new model of diversity, where we prove that the performance of a diverse team improves as the size of the action space increases. Moreover, we show that the performance converges exponentially fast to the optimal one as we increase the number of agents. We present synthetic experiments that give further insights: even though a diverse team outperforms a uniform team when the size of the action space increases, the uniform team will eventually again play better than the diverse team for a large enough action space. We verify our predictions in a system of Go playing agents, where a diverse team improves in performance as the board size increases, and eventually overcomes a uniform team.

Item Type:
Contribution in Book/Report/Proceedings
Subjects:
?? coordination & collaborationdistributed ai team formation ??
ID Code:
81453
Deposited By:
Deposited On:
19 Sep 2016 10:24
Refereed?:
Yes
Published?:
Published
Last Modified:
10 Apr 2024 23:51