The Power of Teams that Disagree: Team Formation in Large Action Spaces

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.

[1]  Leandro Soriano Marcolino,et al.  Multi-Agent Team Formation: Diversity Beats Strength? , 2013, IJCAI.

[2]  Vincent Conitzer,et al.  Common Voting Rules as Maximum Likelihood Estimators , 2005, UAI.

[3]  Lu Hong,et al.  Groups of diverse problem solvers can outperform groups of high-ability problem solvers. , 2004, Proceedings of the National Academy of Sciences of the United States of America.

[4]  Milind Tambe,et al.  Hybrid BDI-POMDP Framework for Multiagent Teaming , 2011, J. Artif. Intell. Res..

[5]  Cha Zhang,et al.  Ensemble Machine Learning: Methods and Applications , 2012 .

[6]  Scott E. Page,et al.  Optimal Forecasting Groups , 2012, Manag. Sci..

[7]  Ariel D. Procaccia,et al.  When do noisy votes reveal the truth? , 2013, EC '13.

[8]  Leandro Soriano Marcolino,et al.  Diverse Randomized Agents Vote to Win , 2014, NIPS.

[9]  Sarvapali D. Ramchurn,et al.  Competing with Humans at Fantasy Football: Team Formation in Large Partially-Observable Domains , 2012, AAAI.

[10]  Manuela M. Veloso,et al.  Modeling and learning synergy for team formation with heterogeneous agents , 2012, AAMAS.

[11]  Christian Guttmann Making Allocations Collectively: Iterative Group Decision Making under Uncertainty , 2008, MATES.

[12]  Huanhuan Chen,et al.  Regularized Negative Correlation Learning for Neural Network Ensembles , 2009, IEEE Transactions on Neural Networks.

[13]  Noa Agmon,et al.  Leading ad hoc agents in joint action settings with multiple teammates , 2012, AAMAS.

[14]  Nikunj C. Oza,et al.  Online Ensemble Learning , 2000, AAAI/IAAI.

[15]  David C. Parkes,et al.  Random Utility Theory for Social Choice , 2012, NIPS.

[16]  An Example of the Misuse of Mathematics in the Social Sciences , 2014 .

[17]  C. List,et al.  Epistemic democracy : generalizing the Condorcet jury theorem , 2001 .

[18]  Sarit Kraus,et al.  Teamwork with Limited Knowledge of Teammates , 2013, AAAI.

[19]  Guandong Xu,et al.  An Integrated Pruning Criterion for Ensemble Learning Based on Classification Accuracy and Diversity , 2012, KMO.

[20]  Marco LiCalzi,et al.  The Power of Diversity Over Large Solution Spaces , 2011, Manag. Sci..