|Kursusnavn (dansk):||Modern AI for Games |
|Kursusnavn (engelsk):||Modern AI for Games |
|Semester:||Efterår 2015 |
|Udbydes under:||cand.it., spil (games) |
|Omfang i ECTS:||15,00 |
|Min. antal deltagere:||12 |
|Forventet antal deltagere:||20 |
|Maks. antal deltagere:||40 |
|Formelle forudsætninger:||Students must have completed a course on programming such as "Introductory Programming", or "Object-Oriented Programming" and "Efficient AI Programming." Having completed the "Game Development" course is a plus. This course will partly cover AI methodologies of the "Efficient AI Programming" module through a clearer game perspective and introduce state-of-the-art topics of advanced game AI. |
|Læringsmål:||After the course the students should be able to:
* Describe and theorize on the AI algorithms covered in the class.
* Identify tasks that can be tackled through advanced AI techniques
and select the appropriate technique for the problem under investigation.
* Compare the performance of different AI techniques and reflect on
their suitability for game AI development.
* Design and implement efficient and robust advanced AI algorithms.
* Work efficiently in groups and evaluate the algorithms in
commercial-standard game productions.
|Fagligt indhold:||Please note, that due to technical challenges, changes may occur before the start of the semester (week 35) – this applies to all sections of the course description.
The primary goal of the course is the understanding, design,
implementation and use of modern artificial intelligence (AI) and
computational intelligence (CI) techniques for generating efficient
intelligent behaviors in games. Additional focus will be given to
state-of-the-art AI algorithms for improving gameplay experience and
game development procedures.
The course will partly cover the following topics (AI techniques and problems):
o Finite-state machines
o Behaviour trees
o Evolutionary algorithms
o Artificial neural networks
o Reinforcement learning
o Hybrid approaches
o Non-player character AI
o Adaptation and learning (off-line and on-line)
o Player behaviour modelling
o Player experience Modeling
o Dynamic difficulty adjustment
o Social simulation
14 weeks of teaching consisting of lectures, exercises and supervision
o 6 weeks of intensive lectures + mandatory individual assignment. The
mandatory individual assignment (6 page written report + source code)
will be handed-in *October 14, 15:00* (*hard deadline*) to the instructor.
Please note that students will not be eligible for the final exam if
they fail on this assignment.
o 8 weeks of group project work with supervision (some lectures are
planned during this period). The group project report (written work +
source code + video production) will be handed-in in learnIT
Students are responsible for attending lectures (some of which will
likely be by outside guest speakers) and then working on their projects
independently (individual mandatory assignment) or in groups. Besides the hours planned for lectures, tutorial, exercise
and supervision sessions are planned which complement the theory covered
during the lectures and are necessary for meeting the learning objectives of the course.
|Obligatoriske aktivititer:||During this course students will be required to hand in an individual mandatory assignment (i.e. report and production), that needs to be completed/approved before being eligible to register for the examination and e.g. being allowed to submit written work for examination. Failure to hand in these mandatory assignments on time will mean that the registration for examination is annulled.
The mandatory assignment is also referred as individual assignment (see above). The mandatory assignment deadline is posted above and at the course blog (*October 14, 15:00*). Additional deadlines are posted separately in learnIT
|Eksamensform og -beskrivelse:||D22: Aflevering med mundtlig eksamen suppleret af aflevering., (7-scale, external exam)|
The total duration of the oral examination is 30 minutes per examinee
|Litteratur udover forskningsartikler:||To be announced |