Multi-agent Team Formation for Design Problems

Design imposes a novel social choice problem: using a team of voting agents, maximize the number of optimal solutions; allowing a user to then take an aesthetical choice. In an open system of design agents, team formation is fundamental. We present the first model of agent teams for design. For maximum applicability, we envision agents that are queried for a single opinion, and multiple solutions are obtained by multiple iterations. We show that diverse teams composed of agents with different preferences maximize the number of optimal solutions, while uniform teams composed of multiple copies of the best agent are in general suboptimal. Our experiments study the model in bounded time; and we also study a real system, where agents vote to design buildings.

[1]  Antonio J. Nebro,et al.  A survey of multi-objective metaheuristics applied to structural optimization , 2014 .

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

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

[4]  John S. Gero,et al.  Complexity Measures as a Basis for Mass Customization of Novel Designs , 2008 .

[5]  Brian P. Bailey,et al.  Improving interaction models for generating and managing alternative ideas during early design work , 2010, Graphics Interface.

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

[7]  Tane Moleta,et al.  Selective interference emergent complexity informed by programmatic, social and performative criteria , 2014 .

[8]  Sebastian Vehlken,et al.  Computational Swarming: A Cultural Technique for Generative Architecture , 2014 .

[9]  David Jason Gerber,et al.  Designing in complexity: Simulation, integration, and multidisciplinary design optimization for architecture , 2014, Simul..

[10]  Frances M. T. Brazier,et al.  Design space exploration revisited , 2006, Artificial Intelligence for Engineering Design, Analysis and Manufacturing.

[11]  V. M. Kureichik,et al.  Parallel genetic algorithms: a survey and problem state of the art , 2010 .

[12]  Mario Sassone,et al.  The early design stage of a building envelope: Multi-objective search through heating, cooling and lighting energy performance analysis , 2015 .

[13]  H. Nurmi.  Comparing Voting Systems , 1987 .

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

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

[16]  Robert F. Woodbury,et al.  Whither design space? , 2006, Artificial Intelligence for Engineering Design, Analysis and Manufacturing.

[17]  Robi Polikar.  Ensemble learning , 2009, Scholarpedia.

[18]  Chao Yang,et al.  A human-computer cooperative particle swarm optimization based immune algorithm for layout design , 2014, Neurocomputing.

[19]  Ariel D. Procaccia,et al.  A Maximum Likelihood Approach For Selecting Sets of Alternatives , 2012, UAI.

[20]  Ariel D. Procaccia,et al.  Better Human Computation Through Principled Voting , 2013, AAAI.

[21]  G. Haynes,et al.  Testing the boundaries of the choice overload phenomenon: The effect of number of options and time pressure on decision difficulty and satisfaction , 2009 .

[22]  Leandro Soriano Marcolino,et al.  Give a Hard Problem to a Diverse Team: Exploring Large Action Spaces , 2014, AAAI.

[23]  Meir Kalech,et al.  Practical voting rules with partial information , 2010, Autonomous Agents and Multi-Agent Systems.

[24]  Naghmi Shireen,et al.  Interacting with Thousands: A Parametric-Space Exploration Method in Generative Design , 2014, Proceedings of the 34th Annual Conference of the Association for Computer Aided Design in Architecture (ACADIA).

[25]  M. Lepper,et al.  The Construction of Preference: When Choice Is Demotivating: Can One Desire Too Much of a Good Thing? , 2006 .

[26]  Michael Donn,et al.  Abstraction versus Case Based: A Comparative Study of Two Approaches to Support Parametric Design , 2015, Proceedings of the 34th Annual Conference of the Association for Computer Aided Design in Architecture (ACADIA).

[27]  Vincent Conitzer,et al.  A Maximum Likelihood Approach towards Aggregating Partial Orders , 2011, IJCAI.

[28]  Edith Elkind,et al.  Electing the Most Probable Without Eliminating the Irrational: Voting Over Intransitive Domains , 2014, UAI.