Training AI for Racing Games Using Reinforcement Learning

A tétel rövid nézete
dc.contributor.advisorHarangi, Balázs
dc.contributor.authorSafa, Ossama
dc.contributor.departmentDE--Informatikai Kar
dc.date.accessioned2025-06-26T21:01:26Z
dc.date.available2025-06-26T21:01:26Z
dc.date.created2025
dc.description.abstractThis thesis explores the application of reinforcement learning in training artificial intelligence agents to navigate a racing game environment. Using Unity's ML-Agents Toolkit and the Proximal Policy Optimization (PPO) algorithm, the study investigates how hyperparameter tuning, reward engineering, and parallel training impact agent performance. A simplified Mario Kart–inspired environment was used to simulate real-time driving challenges. By systematically modifying learning rates, batch sizes, and discount factors, and analyzing their effects, the research identifies optimal training configurations. Additionally, custom reward functions significantly influenced learning efficiency and agent behavior, highlighting the importance of reward design. The findings demonstrate how RL techniques can be effectively applied to both gaming and real-world autonomous driving scenarios.
dc.description.courseProgramtervező informatikus
dc.description.degreeBSc/BA
dc.format.extent45
dc.identifier.urihttps://hdl.handle.net/2437/394791
dc.language.isoen
dc.rights.infoHozzáférhető a 2022 decemberi felsőoktatási törvénymódosítás értelmében.
dc.subjectReinforcement Learning
dc.subjectArtificial Intelligence
dc.subjectMachine Learning
dc.subject.dspaceInformatics::Computer Science
dc.titleTraining AI for Racing Games Using Reinforcement Learning
Fájlok
Eredeti köteg (ORIGINAL bundle)
Megjelenítve 1 - 1 (Összesen 1)
Nincs kép
Név:
thesis.pdf
Méret:
1.52 MB
Formátum:
Adobe Portable Document Format
Leírás:
thesis
Megjelenítés
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:
Letöltés
Gyűjtemények
Theses (IK)