/1
SPIS2001 Machine Learning and Artificial Intelligence in Games
Learning outcomes
By completing the course, the student will have achieved the following learning outcomes:
Knowledge
The student
- understands the complexity of various machine learning (ML) algorithms and their limitations in training
- understands issues and roles of Artificial Intelligence (AI) in the design of games
- understands tactical and strategic AI used in gaming scenario
Skills
The student
- can explain the general idea behind ML, as well as specific algorithms that are being used in real world scenarios
- can use ML methodology for research and industrial settings using current trend of ML software libraries
- can implement and apply ML methods to any chosen game
- can produce game that the avatars are navigate around and served with the purpose based on goal-oriented/utility-theory
- is capable of confidently applying common ML algorithms in practice and implementing their own algorithm
- can perform experiments in ML using real-world game scenario
- can program autonomous movement of avatars
- can design and implement decision making and coordinating action based on heuristic, fuzzy sets or logics
- can read and understand scientific publications on ML/AI and formulate current issues, choice of methods, and results in a short, concise manner
General competence
The student
- is able to plan and carry out varied tasks in accordance with ethical requirements and guidelines
- is familiar with relevant issues of professional ethics, and is able to make a contribution to a professional community
Course content
Central topics:
- Artificial Neural Network
- Q-learning Reinforcement Learning
- Use of popular Machine Learning libraries
- Goal-Oriented Action Planning
- Utility-based Theory
Teaching and working methods
The course is organised as a combination of lectures, practical exercises and supervision.
Coursework requirements
- 3–5 individual assignments for ML and AI respectively
- attendance at lectures in accordance with the teaching plan
- attendance at laboratory teaching in accordance with the teaching plan
Examination
- 1 individual folder assessment on Machine Learning which counts for 50% the final grade
- 1 individual folder assessment on Artificial Intelligence which counts for 50% the final grade
To pass the course, both examinations must receive a passing grade.
Alphabetical grades are used, on a scale from A to F, with E as the lowest passing grade.