prikaz prve stranice dokumenta Evolucijsko učenje agenta za autonomno upravljanje u 2D simulaciji
No public access
undergraduate thesis
Evolucijsko učenje agenta za autonomno upravljanje u 2D simulaciji
2024. urn:nbn:hr:168:526233
Đelekovčan, Stjepan
University of Zagreb
Faculty of Electrical Engineering and Computing

Cite this document

Đelekovčan, S. (2024). Evolucijsko učenje agenta za autonomno upravljanje u 2D simulaciji (Undergraduate thesis). Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing. Retrieved from https://urn.nsk.hr/urn:nbn:hr:168:526233

Đelekovčan, Stjepan. "Evolucijsko učenje agenta za autonomno upravljanje u 2D simulaciji." Undergraduate thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, 2024. https://urn.nsk.hr/urn:nbn:hr:168:526233

Đelekovčan, Stjepan. "Evolucijsko učenje agenta za autonomno upravljanje u 2D simulaciji." Undergraduate thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, 2024. https://urn.nsk.hr/urn:nbn:hr:168:526233

Đelekovčan, S. (2024). 'Evolucijsko učenje agenta za autonomno upravljanje u 2D simulaciji', Undergraduate thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, accessed 14 November 2024, https://urn.nsk.hr/urn:nbn:hr:168:526233

Đelekovčan S. Evolucijsko učenje agenta za autonomno upravljanje u 2D simulaciji [Undergraduate thesis]. Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing; 2024 [cited 2024 November 14] Available at: https://urn.nsk.hr/urn:nbn:hr:168:526233

S. Đelekovčan, "Evolucijsko učenje agenta za autonomno upravljanje u 2D simulaciji", Undergraduate thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, Zagreb, 2024. Available at: https://urn.nsk.hr/urn:nbn:hr:168:526233

Please login to the repository to save this object to your list.
Metadata
TitleEvolucijsko učenje agenta za autonomno upravljanje u 2D simulaciji
Title (english)Evolutionary learning of autonomous control agent in 2D environment
AuthorStjepan Đelekovčan
MentorDomagoj Jakobović (mentor)
Committee memberDomagoj Jakobović (predsjednik povjerenstva)
Committee memberIvan Grubišić (član povjerenstva)
Committee memberLaura Majer (član povjerenstva)
GranterUniversity of Zagreb
Faculty of Electrical Engineering and Computing
Zagreb
Defense date and country2024-06-27, Croatia
Scientific / art field,
discipline and subdiscipline		TECHNICAL SCIENCES
Computing
Abstract
Učenje agenata za igru Thrust koja modelira fizikalnu 2D okolinu i u kojoj je cilj raketom skupiti što više bodova u što kraćem vremenu. Agenti su modelirani neuronskim mrežama i učenje se obavlja koristeći genetski algoritam. U radu je objašnjena teoretska baza prema kojoj je implementiran algoritam te je dan uvid u to kako postavke algoritma i neuronske mreže utječu na rezultate. Postavke učenja optimirane su znanstvenom metodom te je pružen uvid u rezultate.
Abstract (english)
Training of agents for a game called Thrust, which models a physical 2D environment where the goal is to collect as many points as possible in the shortest time. Agents are modelled using neural networks, and training is done using a genetic algorithm. This paper explains the theoretical background using which the algorithm is implemented and gives insight into how training parameters affect the results. Training parameters are optimized using the scientific method, and insight into results is given.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:168:526233
Study programmeTitle: 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 resourceText
File originBorn digital
Access conditionsClosed access
Terms of useLicence In copyright icon
Public note
Created on2024-10-12 20:30:01