Implementing Reinforcement Learning in a fighting video game

dc.contributor.advisorHarangi, Balázs
dc.contributor.authorQudsi, Omar N.S.
dc.contributor.departmentDE--Informatikai Kar
dc.date.accessioned2026-02-12T18:57:19Z
dc.date.available2026-02-12T18:57:19Z
dc.date.created2025-11-06
dc.description.abstractThe following thesis will present the implementation of an Artificial-Intelligence (AI) agent for a 2D fighting game that is developed using Unity, reinforcement learning (RL) is implemented in the form of Unity’s Machine Learning (ML) Agent. The thesis report first surveys AI, ML, RL algorithms and said algorithms’ application in video games, followed by the design of the game environment, state/action/reward representations, as well as the integration of the agent, training, and hyper-parameter tuning which is also discussed. The agent in question will be evaluated in the thesis to examine performance and adaptability, the RL agent learned meaningful tactics, adapted to the player’s patterns through countering the player and throughout testing provided a more engaging experience compared to the previous static AI in the prototype video game, the limitations and directions taken for the duration of the project are discussed.
dc.description.courseMérnökinformatikus
dc.description.degreeBSc/BA
dc.format.extent54
dc.identifier.urihttps://hdl.handle.net/2437/404449
dc.language.isoen
dc.rights.infoHozzáférhető a 2022 decemberi felsőoktatási törvénymódosítás értelmében.
dc.subjectReinforcement Learning
dc.subjectArtificial Intelligence
dc.subjectVideo game
dc.subject.dspaceInformatics::Information Technology
dc.titleImplementing Reinforcement Learning in a fighting video game
Fájlok
Eredeti köteg (ORIGINAL bundle)
Megjelenítve 1 - 1 (Összesen 1)
Nincs kép
Név:
thesis.pdf
Méret:
2.25 MB
Formátum:
Adobe Portable Document Format
Leírás:
thesis
Engedélyek köteg
Megjelenítve 1 - 1 (Összesen 1)
Nincs kép
Név:
license.txt
Méret:
1.95 KB
Formátum:
Item-specific license agreed upon to submission
Leírás:
Gyűjtemények