Markovljev proces odlučivanja i njegova primjena u kontekstu računalnih igara

undergraduate thesis

• Title (english): Markov Decision Process and its Application in the Context of Computer Games
• Author: Sven Cerovec
• Mentor: Bogdan Okreša Đurić (mentor); MBZ: 367114
• Committee member: Markus Schatten (član povjerenstva); MBZ: 291806
• Granter: University of Zagreb; Faculty of Organization and Informatics; (Department of Theoretical and Applied Foundations of Information Sciences); Varaždin
• Defense date and country: 2021-09-24, Croatia
• Scientific / art field, discipline and subdiscipline: SOCIAL SCIENCES; Information and Communication Sciences; Organization and Informatics

Abstract

Creating programs that play games has been around for some time, a while back programmers
were competing to create a program that plays chess perfectly, and they are still refining these
programs today. Classic games like chess are not the only games being affected, with the
increase in popularity of online games, arose a growing interest in gaming artificial intelligence.
Using information and programs made by other people on the internet I built my own that plays
the most popular game in the last decade; League of Legends. What helped make this program
was theory on Markov decision processes which have been used to solve real world problems
in the past. My findings confirmed that with the use of a Markov decision process model for the
creation of my artificial intelligence, it greatly improved the logic behind the bot I was creating.

• Keywords: računalne igre; umjetna inteligencija; markovljevi lanci; markovljev proces odlučivanja; odlučivanje, League of Legends
• Language: croatian
• URN:NBN: urn:nbn:hr:211:794402
• Study programme: Title: Information Systems; Study programme type: university; Study level: undergraduate; Academic / professional title: sveučilišni/a prvostupnik/prvostupnica (baccalaureus/baccalaurea) informatike (sveučilišni/a prvostupnik/prvostupnica (baccalaureus/baccalaurea) informatike)
• Type of resource: Text
• File origin: Born digital
• Access conditions: Open access
• Created on: 2021-09-27 04:28:17