prikaz prve stranice dokumenta Primjena podržanog učenja u simuliranim sustavima
No public access
master's thesis
Primjena podržanog učenja u simuliranim sustavima
Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing, 2018. urn:nbn:hr:168:523866
Livaja, Vladimir Dragutin
University of Zagreb
Faculty of Electrical Engineering and Computing

Institutional repository: FER Repository

Cite this document

Livaja, V. D. (2018). Primjena podržanog učenja u simuliranim sustavima (Master's thesis). Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing. Retrieved from https://urn.nsk.hr/urn:nbn:hr:168:523866

Livaja, Vladimir Dragutin. "Primjena podržanog učenja u simuliranim sustavima." Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, 2018. https://urn.nsk.hr/urn:nbn:hr:168:523866

Livaja, Vladimir Dragutin. "Primjena podržanog učenja u simuliranim sustavima." Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, 2018. https://urn.nsk.hr/urn:nbn:hr:168:523866

Livaja, V. D. (2018). 'Primjena podržanog učenja u simuliranim sustavima', Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, accessed 14 November 2024, https://urn.nsk.hr/urn:nbn:hr:168:523866

Livaja VD. Primjena podržanog učenja u simuliranim sustavima [Master's thesis]. Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing; 2018 [cited 2024 November 14] Available at: https://urn.nsk.hr/urn:nbn:hr:168:523866

V. D. Livaja, "Primjena podržanog učenja u simuliranim sustavima", Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, Zagreb, 2018. Available at: https://urn.nsk.hr/urn:nbn:hr:168:523866

Metadata
TitlePrimjena podržanog učenja u simuliranim sustavima
Title (english)Reinforcement learning in simulated systems
AuthorVladimir Dragutin Livaja
MentorKrešimir Pripužić (mentor)
Committee memberKrešimir Pripužić (predsjednik povjerenstva)
Committee memberDragan Jevtić (član povjerenstva)
Committee memberMarin Vuković (član povjerenstva)
GranterUniversity of Zagreb
Faculty of Electrical Engineering and Computing
Zagreb
Defense date and country2018-07-09, Croatia
Scientific / art field,
discipline and subdiscipline		TECHNICAL SCIENCES
Computing
Abstract
U ovome radu smo se fokusirali na implementaciji podržanoga agenta koji je bio sposoban se adaptirati u razne simulirane sustave i tim putem predstavili kapacitet i moć podržanog učenja. Osnove dubokog učenja su objašnjene u ovome radu. Koristeći se tensorflow-om smo implementirali podržanoga agenta. Agent je evaluiran kroz tri različita simulirana scenarija. Pacman iz Atari 2600 i dva scenarija iz igrice zvane "Doom". Sve evaluacije su grafički prikazane.
Abstract (english)
In this thesis we focused on implementing a reinforcement agent that was able to generalize to various simulated systems and in doing so; showed the ability of the reinforcement learning algorithm to adapt. Fundamentals of deep learning were also described. Using Tensorflow, a reinforcement learning agent was implemented. The agent was evaluated on three different scenarios: Pacman from the Atari 2600 games and two different scenarios of the game Doom. The evaluation results were shown via graphs.
Keywords
Keywords (english)
Languageenglish
URN:NBNurn:nbn:hr:168:523866
Study programmeTitle: Computing
Study programme type: university
Study level: graduate
Academic / professional title: magistar/magistra inženjer/inženjerka računarstva (magistar/magistra inženjer/inženjerka računarstva)
Type of resourceText
File originBorn digital
Access conditionsClosed access
Terms of useLicence In copyright icon
Public note
Created on2019-03-13 22:20:16