Give a hard problem to a diverse team:exploring large action spaces

Soriano Marcolino, Leandro and Xu, Haifeng and Xin Jiang, Albert and Tambe, Milind and Bowring, Emma (2014) Give a hard problem to a diverse team:exploring large action spaces. In: Proceedings of the 28th Conference on Artificial Intelligence (AAAI 2014). Proceedings of the 28th Conference on Artificial Intelligence (AAAI 2014) . UNSPECIFIED, Québec, Canada. ISBN 9781577356615

Full text not available from this repository.

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 not 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 for teams, that is more general than previous models. We prove that the performance of a diverse team improves as the size of the action space gets larger. Concerning the size of the diverse team, we show that the performance converges exponentially fast to the optimal one as we increase the number of agents. We present synthetic experiments that allow us to gain 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 we show a diverse team that improves in performance as the board size increases, and eventually overcomes a uniform team.

Item Type:
Contribution in Book/Report/Proceedings
ID Code:
81371
Deposited By:
Deposited On:
30 Aug 2016 10:54
Refereed?:
Yes
Published?:
Published
Last Modified:
17 Sep 2023 03:58