پديد آورنده :
توكلي ناييني، آرمين
عنوان :
تكامل استراتژي هماهنگ سازي به وسيله برنامه نويسي ژنتيك شبكه اي در دامنه تعقيب ﴿صياد - صيد﴾
مقطع تحصيلي :
كارشناسي ارشد
گرايش تحصيلي :
هوش مصنوعي
محل تحصيل :
اصفهان :دانشگاه صنعتي اصفهان ،دانشكده برق و كامپيوتر
صفحه شمار :
ده ، 91 ، [II]ص. :مصور،جدول،نمودار
يادداشت :
ص.ع. به فارسي و انگليسي
استاد راهنما :
مازيار پالهنگ
استاد مشاور :
محمد حسين سرائي
توصيفگر ها :
يادگيري چند عاملي , الگوريتم ژنتيك , سيستم GNP
تاريخ نمايه سازي :
04/09/86
استاد داور :
فريد شيخ الاسلام ،محمد داورپناه جزي
دانشكده :
مهندسي برق و كامپيوتر
چكيده فارسي :
به فارسي و انگليسي :قابل رؤيت در نسخه ديجيتال
چكيده انگليسي :
AbstractMulti Agent System MAS is a subfield of Distributed Artificial Intelligence DAI thatstudies behaviors of groups of agents and the complexity of their interactions Theidentification design and implementation of strategies for coordination is a central researchissue in the field of DAI It is nearly impossible to identify or even prove the existence of thebest coordination strategy In most cases a coordination strategy is chosen if it is reasonablygood The task of hand coding agent behaviors to achieve desired coordination and teambehaviors is very difficult if not intractable On the other hand The complexity of multi agentproblems can rise with the number of agents and their behavioral sophistication The field ofcooperative multi agent learning promises solutions to these issues by trying to discover agentbehaviors and suggesting new approaches to these problems and as such it has been the focusof numerous studies in recent years Genetic Network Programming GNP is a cooperative multi agent learning method that isproposed recently by inspiration from Genetic Programming GP While GP uses treestructure for representation of solutions GNP uses a network architecture which can improvesolution representation and search ability GNP is a newly proposed search method and has been successfully tested in a few specificdomains Hence its performance should be examined in more various domains In order to acquire the knowledge of using GNP and showing its effectiveness in this thesis this method is applied to evolve a cooperation strategy and a conflict resolution mechanism fora well known domain named pursuit domain Predator Prey This is an easy to describe butdifficult to solve cooperation domain in DAI The results are compared to those of GP andStrongly Typed Genetic Programming STGP The experimental results show the effectiveness of this method in evolving cooperationstrategy between agents in the pursuit domain Its performance seems significantly superior toGP solution and very competitive with STGP solution Also its computation cost is less andthe learning speed is more than these two methods
استاد راهنما :
مازيار پالهنگ
استاد مشاور :
محمد حسين سرائي
استاد داور :
فريد شيخ الاسلام ،محمد داورپناه جزي
