prikaz prve stranice dokumenta Razvoj Android aplikacije za društvene igre temeljen na algoritmima strojnog učenja
Access restricted to authenticated users
master's thesis
Razvoj Android aplikacije za društvene igre temeljen na algoritmima strojnog učenja
2022. urn:nbn:hr:179:939697
Križanović, Frane
University of Split
Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture
Department of Electronics and Computing

Cite this document

Križanović, F. (2022). Razvoj Android aplikacije za društvene igre temeljen na algoritmima strojnog učenja (Master's thesis). Split: University of Split, Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture. Retrieved from https://urn.nsk.hr/urn:nbn:hr:179:939697

Križanović, Frane. "Razvoj Android aplikacije za društvene igre temeljen na algoritmima strojnog učenja." Master's thesis, University of Split, Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture, 2022. https://urn.nsk.hr/urn:nbn:hr:179:939697

Križanović, Frane. "Razvoj Android aplikacije za društvene igre temeljen na algoritmima strojnog učenja." Master's thesis, University of Split, Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture, 2022. https://urn.nsk.hr/urn:nbn:hr:179:939697

Križanović, F. (2022). 'Razvoj Android aplikacije za društvene igre temeljen na algoritmima strojnog učenja', Master's thesis, University of Split, Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture, accessed 24 September 2023, https://urn.nsk.hr/urn:nbn:hr:179:939697

Križanović F. Razvoj Android aplikacije za društvene igre temeljen na algoritmima strojnog učenja [Master's thesis]. Split: University of Split, Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture; 2022 [cited 2023 September 24] Available at: https://urn.nsk.hr/urn:nbn:hr:179:939697

F. Križanović, "Razvoj Android aplikacije za društvene igre temeljen na algoritmima strojnog učenja", Master's thesis, University of Split, Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture, Split, 2022. Available at: https://urn.nsk.hr/urn:nbn:hr:179:939697

Please login to the repository to save this object to your list.
Metadata
TitleRazvoj Android aplikacije za društvene igre temeljen na algoritmima strojnog učenja
Title (english)Development of an Android application for games based on machine learning algorithms
AuthorFrane Križanović
MentorAna Kuzmanić Skelin https://orcid.org/0000-0002-0702-1678 (mentor)
GranterUniversity of Split
Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture
(Department of Electronics and Computing)
Split
Defense date and country2022-09-09, Croatia
Scientific / art field,
discipline and subdiscipline		TECHNICAL SCIENCES
Computing
Abstract
Cilj diplomske radnje je dati pregled fullstack razvoja Android aplikacija te razviti bota algoritmom strojnog učenja koristeći metodu potkrepljenog učenja. Opisana su pravila društvene igre Ultimate Tic Tac Toe i razvijena je mobilna aplikacija kako bi se opisana igra mogla igrati. Za razvoj mobilne aplikacije korišten je Flutter framework te se u diplomskoj radnji nalazi pregled svih značajki tog frameworka korištenih za razvoj modula igrač protiv igrača i modula igrač protiv bota. Za razvoj backend aplikacije korišten je Django framework. U diplomskoj radnji opisane su značajke Django frameworka koje su potpomogle izradi autentikacijskog servisa kako bi se korisnici mogli uspješno prijaviti u sustav. Osim toga, opisan je način na koji su napravljeni endpointi za igrač protiv bota modul igre. Za modul igrač protiv igrača korištene su značajke koje omogućuju implementaciju websocket komunikacije između korisnika aplikacije. Za modul igre igrač protiv AI bota korišten je AlphaZero algoritam. U diplomskoj radnji opisan je način treniranja AlphaZero algoritma i način na koji AlphaZero algoritam radi. AlphaZero algoritam je kombinacija MCTS algoritma za pretragu i neuronske mreže koja popunjava ulogu heuristike u pretrazi najboljeg poteza. U posljednjim poglavljima opisane su cloud tehnologije, Heroku servis koji je korišten za deployment backend aplikacije i način na koji se Django projekt priprema za deployment.
Abstract (english)
The aim of the master thesis is to provide an overview of the fullstack development of Android applications and to develop a bot with a machine learning algorithm using the method of reinforcement learning. Ultimate Tic Tac Toe board game is described and a mobile application is developed to play the described game. The Flutter framework is used for the development of mobile applications and in the master thesis there is an overview of all the features of that framework used for the development of the player vs. player module and the player vs. bot module. The Django framework is used for the development of backend applications. The master thesis describes the features of the Django framework that helped create an authentication service so that users could successfully log in to the system. In addition, the manner in which endpoints are made for the player vs. bot game module is described. The player vs player module uses features that enable the implementation of websocket communication between user applications. The AlphaZero algorithm is used for the player vs. AI bot game module. The master thesis describes how to train the AlphaZero algorithm and how the AlphaZero algorithm works. The AlphaZero algorithm is a combination of the MCTS search algorithm and a neural network that fills the role of heuristics in the search for the best move. The last chapters describe cloud technologies, the Heroku service used to implement backend applications, and the way in which the Django project is prepared for deployment.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:179:939697
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 conditionsAccess restricted to authenticated users
Terms of useLicence In copyright icon
Created on2023-05-25 10:18:41