Podržano učenje u igri Zmija

undergraduate thesis

• Title (english): Reinforcement Learning for Snake Game
• Author: Rikard Orlić
• Mentor: Vladimir Čeperić (mentor)
• Committee member: Vladimir Čeperić (predsjednik povjerenstva)
• Committee member: Marko Barišić (član povjerenstva)
• Committee member: Franjo Matković (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2021-07-06, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Computing

Abstract

U ovom radu se opisuju osnove podržanog učenja te upotrebe podržanog učenja u igrama. Radi se i osvrt na dešavanja u svijetu podržanog učenja danas. Nakon toga se opisuje sustav igrice Zmija te način implementacije rješenja(točnije implementacija Deep Q-learninga) i za kraj se prikažu rezultati dobiveni treniranjem te potencijalna poboljšanja.

Abstract (english)

This paper goes over the basics of reinforcement learning and its use in video games. It also takes a look at what is going on in the world of reinforcement learning today. After that it explains the dynamics of the Snake Game and goes into how the Deep Q-learning algorithm was used to teach an agent. At the end some results of training are shown and some potential upgrades are mentioned.

• Keywords: Podržano učenje; Duboko Q-Učenje; Igra Zmija
• Keywords (english): Reinforcement Learning; Deep-Q Learning; Snake Game
• Language: croatian
• URN:NBN: urn:nbn:hr:168:073310
• 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: 2023-01-14 09:36:37