Akademik Dersler - Tanıtım

Last Updated: 26/06/2026

Code - Course Title	Course Type	Laboratory + Practice	ECTS
OGP219 - Artificial Intelligence in Games	III. SEMESTER	2 +2	5.0

Language of Instruction	Türkçe
Course Type	Required Courses
Course Instructor(s)	ÖĞR. GÖR. GÜVENÇ USANMAZ
Mode of Delivery	This course is delivered through face-to-face instruction. Theoretical lectures and laboratory sessions are integrated throughout the semester. The default engine for practical work is Unity (C#); the instructor may prefer an equivalent game engine (e.g., Unreal Engine, Godot).
Place of Delivery
Used Educational Platforms
Prerequisites	There are no prerequisites or co-requisites for this course.
Courses Recomended	It is recommended to have completed OGP104 Programming II, OGP108 2D Game Development Studio and XXX7965 Data Structures and Algorithms in Games before taking this course. Basic programming, data structures and graph knowledge will facilitate the learning process.
Recommended Resources	Millington, I. & Funge, J. (2009). Artificial Intelligence for Games (2nd ed.). CRC Press — selected chapters.Buckland, M. (2005). Programming Game AI by Example. Wordware — selected chapters.Unity Manual — NavMesh and AI: https://docs.unity3d.com/Unity ML-Agents Toolkit documentation: https://unity-technologies.github.io/ml-agents/
Work Placement	This course has no internship or placement requirement.
Aims of the Course

Weeks	Learning Outcomes	Topics	Teaching Methods
Week - 1		Introduction to game AI; agent concept, NPC, difficulty tuning; how game AI differs from academic AI.
Week - 2		Finite state machines (FSM); states, transitions and hierarchical FSM.
Week - 3		Pathfinding fundamentals; graph and grid representation, the A* algorithm.
Week - 4		Unity NavMesh; agent, obstacle and off-mesh links.
Week - 5		Steering behaviors; seek, flee, arrive, wander.
Week - 6		Perception systems; vision cone, hearing and memory/attention models.
Week - 7		Behavior trees; selector, sequence and decorator nodes.
Week - 8		Utility-based AI; scoring functions and decision making.
Week - 9		Goal-oriented action planning (GOAP) awareness; preconditions and effects.
Week - 10		Group AI; flocking, swarm behavior and simple formations.
Week - 11		Tactical AI; cover, flanking and position selection.
Week - 12		Introduction to learning-based game AI; reinforcement learning awareness and Unity ML-Agents.
Week - 13		AI debugging, visualization and performance; LOD AI and update frequency.
Week - 14		Project presentation; evaluation of the game prototype with an AI module.

No content has been provided.

No content has been provided.

No content has been provided.

Assessment Method and Passing Requirements
	Quamtity	Percentage (%)
Toplam (%)