IT-Universitetet i København
 
  Tilbage Kursusoversigt
Kursusbeskrivelse
Kursusnavn (dansk):Videregående AI i spil 
Kursusnavn (engelsk):Advanced AI in Games 
Semester:Efterår 2009 
Udbydes under:cand.it., medieteknologi og spil (mtg) 
Omfang i ECTS:15,00 
Kursussprog:Engelsk 
Kursushjemmeside:http://www.itu.dk/courses/MVAI/E2009/ 
Min. antal deltagere:
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:The primary goal of the course is the understanding, design,
implementation and use of nouvelle AI techniques for generating efficient
intelligent behaviors in games. Additional focus will be given to
state-of-the-art AI algorithms for improving gameplay experience.

The course will cover the following topics (AI techniques and problems):

AI techniques
o Finite-State Machines
o Fuzzy Logic
o Evolutionary Algorithms
o Artificial Neural Networks
o Reinforcement Learning
o Hybrid Approaches

Tasks/Problems
o Pathfinding
o NPC control at various levels
o Off-line and on-line learning
o Player Satisfaction modeling
o Dynamic Game Balancing
o AI and Affective Computing 
Læringsaktiviteter:14 ugers undervisning bestående af forelæsninger, øvelser og vejledning

o 6 weeks of intensive lectures + mandatory individual assignments. The
individual assignment (6 page written report + source code) will be
handed-in October 9, 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 guest lectures are
planed during this period). The group project report (written work +
production) will be handed-in at the examination office at the end of the
course.

Students are responsible for attending weekly lectures (some of which will
likely be by outside guest speakers) and then working on their projects
independently. Besides the hours planned for lectures, tutorials and
exercise sessions are planned.
.

-------
Study structure - MTG
This course is part of the MTG Technology specialization - find it described here:
MTG specializations
In order to graduate as a MSc in MTG, you need to pass the MTG backbone
courses, and also take a 22,5 ECTS specialization and two 7,5 ECTS electives.

Study structure - SDT
This course is part of the SDT specialization Modern Artificial Intelligence- find it described here:
SDT specializations
In order to graduate as a MSc in SDT, you need to pass the SDT backbone
courses, and also take a 22,5 ECTS specialization and two 7,5 ECTS electives.


Course restriction!!!
There is a course restriction between this course and Advanced Topics in Game Technology offered in the fall 2007. If you took Advanced Topics in Game Technology you cannot take this course!

-----------

Se hvordan undervisningen er tilrettelagt her:
link til skemaoplysninger
Skemaoplysningerne vil være tilgængelige fra kort før semesterstart.

See the schedule here:
link to the time table
The schedule will be available shortly before the beginning of the term.
 

Eksamensform og -beskrivelse:B4: Mundtlig eksamen med skriftlige arbejder men uden forberedelsestid ved eksamen, 7-trins-skala, Ekstern censur

A mandatory individual assignment (6 page written report + source code) must be passed in order to be eligible for the final exam.  

Litteratur udover forskningsartikler:To be announced 
 
Undervisere
Følgende personer underviser på kurset:
NavnStillingUndervisertypeIndsats (%)
Georgios Yannakakis Adjunkt(ITU) Kursusansvarlig 100
Paolo Burelli Ph.d.-studerende(ITU) Underviser 0

Afholdelse (tid og sted)
Kurset afholdes på følgende tid og sted:
UgedagTidspunktForelæsning/ØvelserStedLokale
Tirsdag 10.00-12.00 Forelæsning ITU 2A14
Tirsdag 13.00-15.00 Øvelser ITU 2A54
Torsdag 10.00-12.00 Forelæsning ITU 2A14
Torsdag 13.00-15.00 Øvelser ITU 2A54

Eksamen afholdes på følgende tid og sted:
EksamensdatoTidspunktEksamenstypeStedLokale
2009-12-16 No later than 3 PM Skriftlige arbejder ITU The Examination Office
2010-01-20 Check with the course manager Mundtlig eksamen ITU 2A12
2010-01-21 Check with the course manager Mundtlig eksamen ITU 2A12