Give a Hard Problem to a Diverse Team: Exploring 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 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.

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

[2]  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.

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

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

[5]  Olivier Teytaud,et al.  Modification of UCT with Patterns in Monte-Carlo Go , 2006 .

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

[7]  Martin Müller,et al.  Fuego—An Open-Source Framework for Board Games and Go Engine Based on Monte Carlo Tree Search , 2010, IEEE Transactions on Computational Intelligence and AI in Games.

[8]  Petr Baudis,et al.  PACHI: State of the Art Open Source Go Program , 2011, ACG.

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

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

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

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

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

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

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

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

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

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