Pronalaženje strategije u igrama s više igrača uz pomoć evolucijskih algoritama

undergraduate thesis

• Title (english): Strategy evolution in multiplayer games using evolutionary algorithms
• Author: Ivona Škorjanc
• Mentor: Domagoj Jakobović (mentor)
• Committee member: Domagoj Jakobović (predsjednik povjerenstva)
• Committee member: Ivan Krešo (član povjerenstva)
• Committee member: Marko Đurasević (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2017-07-12, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Computing

Abstract

U radu je objašnjena teorija ponovljenih igara s naglaskom na Iteriranu zatvorenikovu dilemu. Pojašnjene su strategije u toj igri, kako se ponašaju kooperativne i nekooperativne strategije. Ukratko je opisana glavna ideja evolucijskih algoritama. Objašnjeni su svi koraci potrebni za stvaranje programske implementacije: odabir genotipa, definicija funkcije dobrote, biranje ulaznih parametara, prikazivanje poteza u igri, traženje broja generacija te optimalne veličine populacije. Opisan je način na koji je organizirana programska implementacija. Naposljetku su prikazani dobiveni rezultati i zaključci.

Abstract (english)

This paper describes the repeated games theory with emphasis on the Iterated Prisoners Dilemma game. This game's strategies are illustrated: how are the cooperative and non-cooperative strategies behaving. The main idea behind the evolutionary algorithms is briefly described. The paper goes through all the steps needed for creating the software implementation: choosing the genotype, defining the fitness function, choosing the input parameters, representing the game moves, finding the necessary number of generations and the optimal population size. It describes the organization of the implementation components. Finally, the results and conclusions are presented.

• Keywords: ponovljene igre; igre s više igrača; optimizacija strategije; evolucijski algoritmi; genetsko programiranje
• Keywords (english): repeated games; multi-player games; strategy optimization; evolutionary algorithms; genetic programming
• Language: croatian
• URN:NBN: urn:nbn:hr:168:770448
• Study programme: Title: Computing; Study programme type: university; Study level: undergraduate; Academic / professional title: sveučilišni/a prvostupnik/ prvostupnica (baccalaureus/baccalaurea) inženjer/inženjerka računarstva (sveučilišni/a prvostupnik/ prvostupnica (baccalaureus/baccalaurea) inženjer/inženjerka računarstva)
• Type of resource: Text
• File origin: Born digital
• Access conditions: Closed access
• Created on: 2019-03-14 01:19:39