prikaz prve stranice dokumenta Strojno učenje u Unityu
  Download
PDF 1.38 MB
master's thesis
Strojno učenje u Unityu
2018. urn:nbn:hr:200:284605
Bareš, Mateo
Josip Juraj Strossmayer University of Osijek
Faculty of Electrical Engineering, Computer Science and Information Technology Osijek
Department of Software Engineering
Chair of Visual Computing

Cite this document

Bareš, M. (2018). Strojno učenje u Unityu (Master's thesis). Osijek: Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek. Retrieved from https://urn.nsk.hr/urn:nbn:hr:200:284605

Bareš, Mateo. "Strojno učenje u Unityu." Master's thesis, Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, 2018. https://urn.nsk.hr/urn:nbn:hr:200:284605

Bareš, Mateo. "Strojno učenje u Unityu." Master's thesis, Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, 2018. https://urn.nsk.hr/urn:nbn:hr:200:284605

Bareš, M. (2018). 'Strojno učenje u Unityu', Master's thesis, Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, accessed 19 November 2024, https://urn.nsk.hr/urn:nbn:hr:200:284605

Bareš M. Strojno učenje u Unityu [Master's thesis]. Osijek: Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek; 2018 [cited 2024 November 19] Available at: https://urn.nsk.hr/urn:nbn:hr:200:284605

M. Bareš, "Strojno učenje u Unityu", Master's thesis, Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, Osijek, 2018. Available at: https://urn.nsk.hr/urn:nbn:hr:200:284605

Please login to the repository to save this object to your list.
Metadata
TitleStrojno učenje u Unityu
Title (english)Machine learning in Unity
AuthorMateo Bareš
MentorČaslav Livada (mentor)
Committee memberČaslav Livada (predsjednik povjerenstva)
Committee memberAlfonzo Baumgartner (član povjerenstva)
Committee memberKrešimir Nenadić (član povjerenstva)
GranterJosip Juraj Strossmayer University of Osijek
Faculty of Electrical Engineering, Computer Science and Information Technology Osijek
(Department of Software Engineering)
(Chair of Visual Computing)
Osijek
Defense date and country2018-09-28, Croatia
Scientific / art field,
discipline and subdiscipline		TECHNICAL SCIENCES
Computing
Data Processing
Abstract
U ovom diplomskom radu prikazuju se teorijske i praktične mogućnosti Unityj-a u izradi simulacije za učenje inteligentnih agenata algoritmima strojnog učenje. Unity je game engine koji se koristi za razvoj 2D i 3D videoigara, simulacija i interaktivnog sadržaja, a ML-Agents je plugin za Unity koji omogućuje izradu simulacija u kojima se koristi strojno učenje za treniranje inteligentnih agenata u obavljanju određenih zadataka. Strojno učenje obuhvaća metode koje omogućuje računalu da „uči“ obavljati određeni zadatak pomoću unesenih podataka, a bez eksplicitnog programiranja. U sklopu rada izrađen je projekt u kojem inteligentni agent uči korištenjem strojnog učenja s potporom. Zadatak agenta je prolaziti nasumično generiranom cestom i doći do njenog kraja. Na cesti se stvaraju prepreke koje agent mora zaobići, isto tako agent mora obaviti zadatak unutar određenog vremena i ne smije izaći iz granica ceste.
Abstract (english)
This graduate thesis presents theoretical and practical possibilites of Unity in making a simulation for traning intelligent agents with machine learning algorithms. Unity is a game engine which is used for developing 2D and 3D games, simulations and interactive content. ML-Agents is a Unity plugin which enables creating simulations that use machine learning algorithms to train intelligent agents in performing certain tasks. Machine learning encompasses methods that enable a computer to „learn“ to perform a particual task using input data, without explicit programming. Within the thesis project is created in which intelligent agent learns by using reinforcement machine learning. Agent has a task to navigate the randomly generated road and get to its end. Obstacles are created on the road which agent has to avoid, also agent has to complete the task within a certain time and must not leave the road boundaries.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:200:284605
Study programmeTitle: Graduate University Study Programme in Computer Engineering
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 conditionsOpen access
Terms of useLicence In copyright icon
Created on2018-10-17 08:18:26