Razvoj modela strojnog učenja koji igra video igru žanra platformer u alatima Unity i TensorFlow

master's thesis

• Title (english): Developing a Machine Learning Model for Playing a Platformer Video Game in Unity and TensorFlow
• Author: Dario Alilović
• 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: 2022-09-26, Croatia
• Scientific / art field, discipline and subdiscipline: SOCIAL SCIENCES; Information and Communication Sciences; Organization and Informatics

Abstract

This thesis deals with game development and the use of artificial intelligence in the domain of video games, especially artificial neural networks. It covers some of the basics of game development in the Unity game engine, as well as some basics of machine learning and artificial intelligence. Basically, it follows the process of developing a platform game using the Unity game engine and applying a deep q learning algorithm, developed using the Python library TensorFlow, to teach the agent how to play said game. The thesis concludes that Unity is an excellent reinforcement learning tool since it provides a secure and modular environment in which agents can learn.

• Keywords: umjetna inteligencija; unity; strojno učenje; TensorFlow; videoigre; platformer
• Language: croatian
• URN:NBN: urn:nbn:hr:211:449377
• Study programme: Title: Information and Programming Engineering; Study programme type: university; Study level: graduate; Academic / professional title: magistar/magistra informatike (magistar/magistra informatike)
• Type of resource: Text
• File origin: Born digital
• Access conditions: Open access
• Created on: 2022-10-03 04:26:11