پديد آورنده :
مجيدي، سعيد
عنوان :
به كارگيري روش يادگيري تقويتي براي مسيريابي پويا در شبكه به عنوان يك سيستم چندعاملي
مقطع تحصيلي :
كارشناسي ارشد
گرايش تحصيلي :
هوش مصنوعي
محل تحصيل :
اصفهان: دانشگاه صنعتي اصفهان، دانشكده برق و كامپيوتر
صفحه شمار :
ده، 94، [II] ص.: مصور، جدول، نمودار
يادداشت :
ص. ع. به فارسي و انگليسي
استاد راهنما :
مسعودرضا هاشمي
استاد مشاور :
مازيار پالهنگ
توصيفگر ها :
يادگيري Q , الگوريتم مسيريابي
تاريخ نمايه سازي :
6/6/86
استاد داور :
جمال گلستاني، جواد عسكري
دانشكده :
مهندسي برق و كامپيوتر
چكيده فارسي :
به فارسي و انگليسي: قابل رويت در نسخه ديجيتال
چكيده انگليسي :
AbstractComputer networks are important examples of distributed dynamic systems Distributed control in these systems especially at the routing level is necessary tomake the network behavior adaptive to changes in topology data traffic services etc Recently researchers have investigated new routing algorithms which provide betteradaptivity building on advances in machine learning Reinforcement Learning is anunsupervised learning method which its goal is to learn a policy a map fromperceptions to actions based on the feedback received from the environment Thislearning task can be viewed as a search of policies which are evaluated through theirinteractions with the environment Q learning is one of the most applicablereinforcement learning algorithms In this thesis network is modeled as a multiagentsystem in which every router represents an agent Each agent uses q learning to learnthe states of the network to choose the best possible action for each state In thismodel the status of each node is defined as a function of the status of adjacent nodesand its links to them So any changes in the status of a link or a node affects the statesof adjacent nodes agents and cause them to take more appropriate actions based ontheses changes
استاد راهنما :
مسعودرضا هاشمي
استاد مشاور :
مازيار پالهنگ
استاد داور :
جمال گلستاني، جواد عسكري
