||Lectures and assignments (online feedback 1 hour per week)
||50% written exam, 50% assignment(s)
|Studielast:||6 ECTS credits
|Inschrijving:||This course has a maximum capacity of 40 participants. If you filled out the survey you received recently (“selecting master courses CIS Fall semester 2016) you will be enrolled automatically. Other students: see specifics.
|Blackboard informatie||Link to
Blackboard (Als u de melding 'Guest are not allowed in this course' krijgt, dient u nog bij Blackboard in te loggen)
The course objectives are:
Doel van de cursus (alleen in het Engels beschikbaar)
- Discussing and reasoning about game design and game intelligence
- Understanding and applying simple game theory
- Understanding and applying decision making techniques
- Understanding and applying strategies and tactics
- Understanding and applying learning techniques
Inhoud van de cursus (alleen in het Engels beschikbaar)
In the modern world, people's lives are increasingly spent in virtual worlds. Games are used not only for entertainment, but also for training, education, and social interaction. While people spend their time in virtual environments, they interact with virtual beings, controlled by the compter.
The goal of the course is to make the students understand how natural behavior can be created in virtual environments, and how to implement artificial behavior in virtual environments. Artificial intelligence in games allows a computer to play a game, or be an integral part of a world in a game. The course discusses how such artificial intelligence is created, what techniques are used in state-of-the-art games, and which techniques will be used in the future of games.
The following subjects will be discussed during the course:
- Game artificial intelligence
- Game theory (classification, Nash equilibrium, other equilibria)
- Decision making (heuristics, decision trees, state machines, fuzzy logic, goal-oriented behavior, rule-based systems, scripting)
- Tactics and strategies (waypoints, influence maps, tactical analysis)
- Learning (hillclimbing, annealing, N-grams, decision-tree learning, reinforcement learning, dynamic scripting, player modeling)
- Classic and modern board game AI (game complexity, tree search, MCTS)
The students will form small groups to do an assignment. The assignment concerns the creation of an artificial intelligence for a game. This will be an opponent intelligence, which will compete with the intelligences created by other student groups. The computer language needed to do this assignment (NWScript) is rather straightforward, and will be introduced to the students during the course. Some knowledge of programming (for instance acquired through a Research Skills module) is helpful, though not required.
Bijzonderheden (alleen in het Engels beschikbaar)
This course has a maximum capacity of 40 participants. If you filled out the survey you received recently (selecting master courses CIS Fall semester 2016) you will be enrolled automatically. All other students have to send an e-mail to: mastercoursesCIW@uvt.nl and will be enrolled if places are available.
Every week there will be a lecture. The remainder of the time will be used by the students to work on the assignment. The lecturer or an assistant will mostly be present to help the students.
The students deliver the results of the assignment as a group, and a short report on the assignment. The assignment result and the reports will be graded.
At the end of the course there will be a written exam. The final grade for the course is determined for 50% by the assignment, and for 50% by the written exam.
- Ian Millington, Artificial Intelligence for Games, Morgan Kaufmann, 2006, ISBN 978-0124977822. Second edition can be used as well
Some knowledge of programming is helpful.
Mogelijk interessant voor
- Bedrijfscommunicatie en Digitale Media (
- Interculturele Communicatie (
- Communicatie-Design (
- Human aspects of Information Technology (
- Data Journalism (
- Communication and Information Sciences (