Evolution of division of labor in artificial societies

Created by W.Langdon from gp-bibliography.bib Revision:1.4549

  author =       "Pawel Lichocki",
  title =        "Evolution of division of labor in artificial
  school =       "Ecole Polytechnique Federale de Lausanne",
  year =         "2013",
  address =      "Switzerland",
  month =        "22 " # mar,
  keywords =     "genetic algorithms, genetic programming, artificial
                 evolution, multi-agent systems, cooperation, division
                 of labour, specialisation, team composition, task
                 allocation, response thresholds, artificial neural
                 networks, simulations, evolutionary computation,
                 selection method, crossover. Evolution artificielle,
                 systemes multi-agents, cooporation, division du
                 travail, specialisation, composition des equipes,
                 allocation des taches, seuil de raponse, reseaux
                 neuronaux artificiels, simulations, algorithmes
                 evolutionnaires, methode de selection, enjambement",
  URL =          "http://infoscience.epfl.ch/record/184959/files/EPFL_TH5687.pdf",
  size =         "162 pages",
  abstract =     "Natural and artificial societies often divide the
                 workload between specialised members. For example, an
                 ant worker may preferentially perform one of many tasks
                 such as brood rearing, foraging and nest maintenance. A
                 robot from a rescue team may specialise in search,
                 obstacle removal, or transportation. Such division of
                 labour is considered crucial for efficient operation of
                 multi-agent systems and has been studied from two
                 perspectives. First, scientists address the how
                 question seeking for mechanical explanations of
                 division of labour. The focus has been put on
                 behavioural and environmental factors and on task
                 allocation algorithms leading to specialisation.
                 Second, scientists address the why question uncovering
                 the origins of division of labour. The focus has been
                 put on evolutionary pressures and optimisation
                 procedures giving rise to specialisation. Studies have
                 usually addressed one of these two questions in
                 isolation, but for a full understanding of division of
                 labour the explanation of the origins of specific
                 mechanisms is necessary. Here, we rise to this
                 challenge and study three major transitions related to
                 division of labour. By means of theoretical analyses
                 and evolutionary simulations, we construct a pathway
                 from the occurrence of cooperation, through fixed
                 castes, up to dynamic task allocation.

                 First, we study conditions favouring the evolution of
                 cooperation, as it opens the doors for the potentially
                 following specialisation. We demonstrate that these
                 conditions are sensitive to the mechanisms of
                 intra-specific selection (or selection methods). Next,
                 we take an engineering perspective and we study
                 division of labour at the genetic level in teams of
                 artificial agents. We devise efficient algorithms to
                 evolve fixed assignments of agents to castes (or team
                 compositions). To this end, we propose a novel
                 technique that exchanges agents between teams, which
                 greatly eases the search for the optimal composition.
                 Finally, we take a biological perspective and we study
                 division of labour at the behavioural level in
                 simulated ant colonies. We quantify the efficiency of
                 task allocation algorithms, which have been used to
                 explain specialisation in social insects. We show that
                 these algorithms fail to induce precise reallocation of
                 the workforce in response to changes in the
                 environment. We overcome this issue by modelling task
                 allocation with artificial neural networks, which lead
                 to near optimal colony performance.

                 Overall, this work contributes both to biology and to
                 engineering. We shed light on the evolution of
                 cooperation and division of labour in social insects,
                 and we show how to efficiently optimise teams of
                 artificial agents. We resolve the encountered
                 methodological issues and demonstrate the power of
                 evolutionary simulations to address biological
                 questions and to tackle engineering problems.",
  notes =        "Is this GP?

                 EPFL Presentee le 22 mars 2013 Suisse

                 THESE NO 5687 (2013)

                 acceptee sur proposition du jury: Prof. A. Billard,
                 presidente du jury Prof. D. Floreano, Prof. L. Keller,
                 directeurs de these Prof. M.-O. Hongler, rapporteur
                 Prof. L. Lehmann, rapporteur",

Genetic Programming entries for Pawel Lichocki