prikaz prve stranice dokumenta Razvoj algoritma za igranje trešete korištenjem potpornog učenja
No public access
undergraduate thesis
Razvoj algoritma za igranje trešete korištenjem potpornog učenja
Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing, 2020. urn:nbn:hr:168:499377
Turina, Marko
University of Zagreb
Faculty of Electrical Engineering and Computing

Institutional repository: FER Repository

Cite this document

Turina, M. (2020). Razvoj algoritma za igranje trešete korištenjem potpornog učenja (Undergraduate thesis). Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing. Retrieved from https://urn.nsk.hr/urn:nbn:hr:168:499377

Turina, Marko. "Razvoj algoritma za igranje trešete korištenjem potpornog učenja." Undergraduate thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, 2020. https://urn.nsk.hr/urn:nbn:hr:168:499377

Turina, Marko. "Razvoj algoritma za igranje trešete korištenjem potpornog učenja." Undergraduate thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, 2020. https://urn.nsk.hr/urn:nbn:hr:168:499377

Turina, M. (2020). 'Razvoj algoritma za igranje trešete korištenjem potpornog učenja', Undergraduate thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, accessed 22 November 2024, https://urn.nsk.hr/urn:nbn:hr:168:499377

Turina M. Razvoj algoritma za igranje trešete korištenjem potpornog učenja [Undergraduate thesis]. Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing; 2020 [cited 2024 November 22] Available at: https://urn.nsk.hr/urn:nbn:hr:168:499377

M. Turina, "Razvoj algoritma za igranje trešete korištenjem potpornog učenja", Undergraduate thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, Zagreb, 2020. Available at: https://urn.nsk.hr/urn:nbn:hr:168:499377

Metadata
TitleRazvoj algoritma za igranje trešete korištenjem potpornog učenja
Title (english)Developing a tressete-playing algorithm using reinforcement learning
AuthorMarko Turina
MentorMarija Seder (mentor)
Committee memberMarija Seder (predsjednik povjerenstva)
Committee memberFilip Marić (član povjerenstva)
Committee memberLuka Petrović (član povjerenstva)
GranterUniversity of Zagreb
Faculty of Electrical Engineering and Computing
Zagreb
Defense date and country2020-09-15, Croatia
Scientific / art field,
discipline and subdiscipline		TECHNICAL SCIENCES
Computing
Abstract
Ovaj rad obrađuje potporno učenje i implementaciju te vrste strojnog učenja kroz trešetu, talijansku igru udomaćenu na hrvatskom priobalju i otocima. Ukratko objašnjava trešetu i pravila igre. Objašnjava principe potpornog učenja te navodi prednosti i nedostatke u odnosu na druge vrste strojnog učenja. Na primjeru trešete implementira agenta koji nauči igrati tu (za čovjeka) jednostavnu igru te kroz statistiku pokazuje napredak učenja. Na kraju testira naučenog agenta igranjem protiv čovjeka koji je dugogodišnji majstor trešete.
Abstract (english)
This paper deals with reinforcement learning and the implementation of this type of machine learning through tressete, an Italian game domesticated on the Croatian coast and islands. The paper briefly explains the tressette and the rules of the game. This paper explains the principle of reinforcement learning and shows the advantages and disadvantages in relation to other types of machine learning. Reinforcement learning agent learns to play tressete. Progress of learning is shown through statistics. At the end of the paper, the learned agent plays against a human master of tressette to test the reinforcement learning concept.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:168:499377
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 on2023-01-14 10:10:15