Προηγμένη αντιδραστική συμπεριφορά τεχνητής νοημοσύνης σε εικονικές προσομοιώσεις
Advanced artificial intelligence reactive behaviour in virtual simulations
![Thumbnail](/xmlui/bitstream/handle/unipi/16672/Charitoudis_17178.pdf.jpg?sequence=6&isAllowed=y)
Bachelor Dissertation
Author
Χαριτούδης, Απόστολος - Ανδρέας
Date
2024-07Advisor
Παναγιωτόπουλος, ΘεμιστοκλήςView/ Open
Keywords
Βιντεοπαιχνίδια ; Τεχνητή νοημοσύνη ; Μηχανική μάθηση ; Μηχανή πεπερασμένων καταστάσεων ; Υβριδικές τεχνικές ; Video games ; Artificial intelligence ; Machine learning ; Finite state machine ; Hybrid techniquesAbstract
This dissertation explores the integration of Machine Learning (ML) and Finite State Machines (FSM) in the development of Artificial Intelligence (AI) in video games, focusing on Prescripted Reactive Behavior. Through a critical analysis of three key studies, the effectiveness of hybrid AI techniques in enhancing AI capabilities in video games is evaluated. The findings indicate that the combination of ML and FSM improves the adaptability and complexity of AI, enabling more realistic and engaging behaviors. Additionally, the limitations of manual research and the possibility that some relevant studies may not have been included are acknowledged. The dissertation contributes to the synthesis of current knowledge, identifies research gaps, and provides practical recommendations, highlighting the potential benefits of interdisciplinary approaches in AI development in the researched field.
The scientific field of this dissertation is Artificial Intelligence in the context of video games with a particular focus on the integration of Machine Learning and Finite State Machines.