Evaluation Mechanism of Collective Intelligence for Heterogeneous Agents Group

Collective intelligence is manifested when multiple agents coherently work in observation, interaction, decision-making and action. In this paper, we define and quantify the intelligence level of heterogeneous agents group organized in a flat structure without explicit leadership by the improved Anytime Universal Intelligence Test (AUIT), an extension of the existing evaluation of homogeneous agents group. The relationship of intelligence level with agents’ composition, group size, spatial complexity and testing time is analyzed. The intelligence level of heterogeneous agents groups is compared with that for the homogeneous groups as well, so as to demonstrate the effects of heterogeneity on collective intelligence. Our work will contribute to understand the essence of collective intelligence more deeply and reveal the effect of various key factors on group intelligence level.

[1]  Nan Li,et al.  Optimization Performance Comparison of Three Different Group Intelligence Algorithms on a SVM for Hyperspectral Imagery Classification , 2019, Remote. Sens..

[2]  J. Fadul.  Collective Learning: Applying Distributed Cognition for Collective Intelligence , 2009 .

[3]  David G. Green,et al.  Factors of Collective Intelligence: How Smart Are Agent Collectives? , 2016, ECAI.

[4]  José Hernández-Orallo,et al.  Beyond the Turing Test , 2000, J. Log. Lang. Inf..

[5]  Kagan Tumer,et al.  An Introduction to Collective Intelligence , 1999, ArXiv.

[6]  Jerzy Korczak,et al.  Collective Intelligence Supporting Trading Decisions on FOREX Market , 2017, ICCCI.

[7]  Tadeusz Szuba,et al.  A formal definition of the phenomenon of collective intelligence and its IQ measure , 1999, Future generations computer systems.

[8]  Ming Li,et al.  An Introduction to Kolmogorov Complexity and Its Applications , 2019, Texts in Computer Science.

[9]  Hiroki Sayama,et al.  Collective decision making, leadership, and collective intelligence: Tests with agent-based simulations and a Field study , 2016 .

[10]  Nader Chmait,et al.  Understanding and Measuring Collective Intelligence Across Different Cognitive Systems: An Information-Theoretic Approach , 2017, IJCAI.

[11]  Francesco Guala,et al.  Heterogeneous Agents in Public Goods Experiments , 2005 .

[12]  I. René J. A. te Boekhorst,et al.  Pattern Formation in Homogeneous and Heterogeneous Swarms: Differences Between Versatile and Specialized Agents , 2007, 2007 IEEE Symposium on Artificial Life.

[13]  John Fox,et al.  Understanding intelligent agents: analysis and synthesis , 2003, AI Commun..

[14]  A. Woolley,et al.  Collective Intelligence and Group Performance , 2015 .

[15]  David L. Dowe,et al.  A Dynamic Intelligence Test Framework for Evaluating AI Agents , 2016 .

[16]  José Hernández-Orallo,et al.  Measuring universal intelligence: Towards an anytime intelligence test , 2010, Artif. Intell..

[17]  Peter Krafft,et al.  A Simple Computational Theory of General Collective Intelligence , 2018, Top. Cogn. Sci..

[18]  José Hernández-Orallo.  On environment difficulty and discriminating power , 2014, Autonomous Agents and Multi-Agent Systems.

[19]  Yuan-Fang Li,et al.  An Information-Theoretic Predictive Model for the Accuracy of AI Agents Adapted from Psychometrics , 2017, AGI.

[20]  Michael S. Bernstein,et al.  Handbook of Collective Intelligence , 2015 .

[21]  José Hernández-Orallo,et al.  Instrumental Properties of Social Testbeds , 2015, AGI.

[22]  Keri Schreiner.  Measuring IS: Toward a US Standard , 2000, IEEE Intell. Syst..

[23]  F. Yammarino,et al.  A new kind of organizational behavior , 2009 .

[24]  Bill Hibbard.  Measuring Agent Intelligence via Hierarchies of Environments , 2011, AGI.

[25]  José Hernández-Orallo,et al.  On the influence of intelligence in (social) intelligence testing environments , 2012, ArXiv.

[26]  Manuela M. Veloso,et al.  Weighted synergy graphs for effective team formation with heterogeneous ad hoc agents , 2014, Artif. Intell..

[27]  Itamar Arel,et al.  Beyond the Turing Test , 2009, Computer.

[28]  Nicolas Christin,et al.  Security and insurance management in networks with heterogeneous agents , 2008, EC '08.

[29]  T. C. Jannett,et al.  Measuring Machine Intelligence of an Agent-Based DistributedSensor Network System , 2007 .

[30]  Ngoc Thanh Nguyen,et al.  A Method for Improving the Quality of Collective Knowledge , 2015, ACIIDS.

[31]  David L. Dowe,et al.  A Non-Behavioural, Computational Extension to the Turing Test , 1998 .

[32]  David Weschsler,et al.  Concept of collective intelligence. , 1971 .

[33]  K. Williams,et al.  Many Hands Make Light the Work: The Causes and Consequences of Social Loafing , 1979 .

[34]  L DoweDavid,et al.  Measuring Universal Intelligence in Agent-Based Systems Using the Anytime Intelligence Test , 2016 .

[35]  Maja J. Matarić,et al.  From Local Interactions to Collective Intelligence , 1995 .

[36]  Iain D Couzin,et al.  Modular structure within groups causes information loss but can improve decision accuracy , 2019, Philosophical Transactions of the Royal Society B.

[37]  David G. Green,et al.  Observation, Communication and Intelligence in Agent-Based Systems , 2015, AGI.

[38]  P.-P. Grasse.  La reconstruction du nid et les coordinations interindividuelles chezBellicositermes natalensis etCubitermes sp. la théorie de la stigmergie: Essai d'interprétation du comportement des termites constructeurs , 1959, Insectes Sociaux.

[39]  Herbert Dawid,et al.  Macroeconomics with heterogeneous agent models: fostering transparency, reproducibility and replication , 2018, Journal of Evolutionary Economics.

[40]  Sean Luke,et al.  Cooperative Multi-Agent Learning: The State of the Art , 2005, Autonomous Agents and Multi-Agent Systems.

[41]  Shi-Jinn Horng,et al.  The chessboard distance transform and the medial axis transform are interchangeable , 1996, Proceedings of International Conference on Parallel Processing.

[42]  Arthur C. Graesser,et al.  Is it an Agent, or Just a Program?: A Taxonomy for Autonomous Agents , 1996, ATAL.

[43]  Lynne E. Parker,et al.  Metrics for quantifying system performance in intelligent, fault-tolerant multi-robot teams , 2007, 2007 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[44]  D. Meyer,et al.  Supporting Online Material Materials and Methods Som Text Figs. S1 to S6 References Evidence for a Collective Intelligence Factor in the Performance of Human Groups , 2022 .

[45]  Shane Legg,et al.  A Formal Measure of Machine Intelligence , 2006, ArXiv.

[46]  Sang Joon Kim,et al.  A Mathematical Theory of Communication , 2006 .

[47]  Ngoc Thanh Nguyen,et al.  INCONSISTENCY OF KNOWLEDGE AND COLLECTIVE INTELLIGENCE , 2008, Cybern. Syst..

[48]  Lawrence F. Gray,et al.  A Mathematician Looks at Wolfram''s New Kind of Science , 2003 .