prikaz prve stranice dokumenta Implementacija Q-learning algoritma u Unity ML-agents alate
Access restricted to students and staff of home institution
master's thesis
Implementacija Q-learning algoritma u Unity ML-agents alate
2023. urn:nbn:hr:200:684508
Stipančić, Damir
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

Stipančić, D. (2023). Implementacija Q-learning algoritma u Unity ML-agents alate (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:200:684508

Stipančić, Damir. "Implementacija Q-learning algoritma u Unity ML-agents alate." Master's thesis, Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, 2023. https://urn.nsk.hr/urn:nbn:hr:200:684508

Stipančić, Damir. "Implementacija Q-learning algoritma u Unity ML-agents alate." Master's thesis, Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, 2023. https://urn.nsk.hr/urn:nbn:hr:200:684508

Stipančić, D. (2023). 'Implementacija Q-learning algoritma u Unity ML-agents alate', Master's thesis, Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, accessed 31 December 2024, https://urn.nsk.hr/urn:nbn:hr:200:684508

Stipančić D. Implementacija Q-learning algoritma u Unity ML-agents alate [Master's thesis]. Osijek: Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek; 2023 [cited 2024 December 31] Available at: https://urn.nsk.hr/urn:nbn:hr:200:684508

D. Stipančić, "Implementacija Q-learning algoritma u Unity ML-agents alate", Master's thesis, Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, Osijek, 2023. Available at: https://urn.nsk.hr/urn:nbn:hr:200:684508

Please login to the repository to save this object to your list.
Metadata
TitleImplementacija Q-learning algoritma u Unity ML-agents alate
Title (english)Implementation of Q-learning algorithm in Unity ML-agents
AuthorDamir Stipančić
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 country2023-04-12, Croatia
Scientific / art field,
discipline and subdiscipline		TECHNICAL SCIENCES
Computing
Artificial Intelligence
Abstract
Diplomski rad obrađuje temu izrade vlastitog algoritma strojnog učenja i njegovu implementaciju u sklopu Unity ML Agents alata. Algoritam se onda koristi za učenje agenta u Unity okruženju. Algoritam je pisan u Python programskom jeziku, okruženje i agent unutar Unity alata. Kombiniranje ovih alata uz pomoć „mlagents“ biblioteke dovodi do uspješnog rješenja predstavljenog problema. ML Agents alati su velikim dijelom zasnovani na Python programskom jeziku i to je glavni dio eksperimenta koji omogućava realizaciju najbitnijih dijelova. Konstantan proces unaprjeđivanja ovih alata znači da se ovi alati i povezane mogućnosti konstantno razvijaju te bi trebali s vremenom postati sve pristupačniji i moćniji te omogućiti kompleksnija rješenja.
Abstract (english)
This paper covers the topic of implementing your own custom machine learning algorithm which can then be implemented within the already existing Unity ML Agents framework. This algorithm is used to train a simple agent within a simple Unity Environment. The Environment and the Agent logic has been implemented within the Unity itself and the machine learning algorithm has been implemented in Python. The combination of these tools using the “mlagents” library in Python allows for a successful solution of the presented problem. Python is a large part of the ML Agents toolkit, and it is Python itself which enables the successful implementation of all major components of this experiment. The constant process of improvement that these tools are exposed to means that with time they should only become more accessible and more powerful, enabling more complex solutions to be achieved.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:200:684508
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 conditionsAccess restricted to students and staff of home institution
Terms of useLicence In copyright icon
Created on2023-05-08 10:56:53