-
Presentation
Presentation
This course aims to confer competences in the field of Artificial Intelligence oriented to the development of video games (AIVG), providing students with solid and structured knowledge that allows them to understand theoretical concepts and develop code for solving practical problems in AIVG.
-
Class from course
Class from course
-
Degree | Semesters | ECTS
Degree | Semesters | ECTS
Bachelor | Semestral | 6
-
Year | Nature | Language
Year | Nature | Language
2 | Optional | Português
-
Code
Code
ULHT1075-2129
-
Prerequisites and corequisites
Prerequisites and corequisites
Not applicable
-
Professional Internship
Professional Internship
Não
-
Syllabus
Syllabus
AI basics for games. Motion and intelligent motion: 2D and 3D motion, direction / driving, location prediction. Path search, orientation and navigation: graphs, Dijkstra and A * algorithms, navigation grids and meshes, cost functions; coordinated, emergent and waypoint motion. Decisions: decision trees, state machines, behavior trees, other approaches. Learning: Basics, hill climbing, annealing, genetic algorithms, action prediction, Naive Bayes Classifiers, other approaches. Board games: basics, family of minimax algorithms, MCTS, other approaches. Procedural content generation
-
Objectives
Objectives
Understanding the basics of Artificial Intelligence for video games. Understanding of basic and intermediate concepts of intelligent movement and path finding in video games. Understanding of intermediate and advanced concepts in decision making by video game agents, namely state machines, behavior trees, among others. Understanding of basic concepts of learning in video games. Understanding of Artificial Intelligence topics in board games. Ability to solve problems involving acquired concepts, both abstract and practical (i.e. programming).
-
Teaching methodologies
Teaching methodologies
Use of active learning prototypes, as described in: Fachada, N., Barreiros, F.F., Lopes, P., & Fonseca, M. (2023). Active Learning Prototypes for Teaching Game AI. In 2023 IEEE Conference on Games (CoG). IEEE. Organizing AI competitions for games, as described in: Fachada, N. (2021). ColorShapeLinks: A board game AI competition for educators and students. Computers and Education: Artificial Intelligence, 2, 100014. Optional research component after the normal period of continuous assessment, with the aim of students producing a scientific article of their own, such as: Fernandes, P. M. et al. (2020). SimpAI: Evolutionary heuristics for the ColorShapeLinks board game competition. In International Conference on Videogame Sciences and Arts (pp. 113-126). Springer. Silva, R. C., Fachada, N., De Andrade, D., & Códices, N. (2022). Procedural generation of 3D maps with snappable meshes. IEEE Access, 10, 43093-43111.
-
References
References
Millington, I. (2019). AI for Games (3rd ed.). CRC Press.
-
Assessment
Assessment
Época normal (avaliação contínua)
- Componente teórica: 2 frequências correspondendo a 45% (22.5% + 22.5%) da nota + 5% apresentação (nota mínima: 9 valores na média ponderada).
- Componente prática: 2 projetos correspondendo a 45% (22.5% + 22.5%) da nota + 5% apresentação (nota mínima: 9 valores na média ponderada).
- Componente de investigação (opcional): permite subir a nota final até 5 valores, está condicionada à aprovação nas componentes teórica e prática.
- A frequência das aulas é obrigatória de acordo com o artigo 11º do Regulamento Geral de Avaliação da Universidade Lusófona.
Época de recurso
- Exame teórico (50% da nota final, nota mínima: 9 valores)
- Projeto prático (50% da nota final, nota mínima: 9 valores)
Época especial
- Exame teórico (50% da nota final, nota mínima: 9 valores)
- Projeto prático (50% da nota final, nota mínima 9: valores)
- A avaliação de época especial está disponível de acordo com os regulamentos da Universidade Lusófona.
-
Mobility
Mobility
No
