IT-Universitetet i København
 
  Tilbage Kursusoversigt
Kursusbeskrivelse
Kursusnavn (dansk):AI i spilprogrammering 
Kursusnavn (engelsk):AI in Game Programming 
Semester:Efterår 2006 
Udbydes under:cand.it., medieteknologi og spil (mtg) 
Omfang i ECTS:15,00 
Kursussprog:Engelsk 
Kursushjemmeside:http://www.itu.dk/courses/MAGP/E2006/index.html 
Min. antal deltagere:0 
Forventet antal deltagere:50 
Maks. antal deltagere:80 
Formelle forudsætninger:You must have passed both the Game Programming course, or equivalent, and the Basic Programming course, or equivalent. Essentially, this implies that prior to the AI in Game Programming course, you should

_ be able to write programs in C++ [or any comparable language]
_ know how basic AI is used in games

In addition, a very rudimentary knowledge of statistics and vector calculus would be beneficial, but is not necessarily a prerequisite.
 
Læringsmål:"It would appear that we have reached the limits of what it is possible to achieve with computer technology, although one should be careful with such statements, as they tend to sound pretty silly in 5 years"
--- John von Neumann

The objective of the course is to introduce the students to a variety of artificial intelligence concepts, methods, and algorithms related to and applicable in games. The main focus will be on the emerging field of [statistical] learning. This aims, for example, at enabling the computer to adapt its skills to the player's based on experience. The course's emphasis will be on the actual AI concepts and, as such, not necessarily their use in games.

After the course the student is skilled in one or more of the following topics:

_ providing a general overview of main approaches to learning in games
_ applying machine learning techniques
_ ...and recognizing their conection to games
_ applying genetic algorithms
_ using and implementing neural networks
_ predicting the future
_ building a finite state machine
_ lunar landings
_ developing your own intelligent game
_ applying reinforcement learning
 
Fagligt indhold:Besides the appropriate motivation to the theory and practice of artificial intelligence with a focus on games, the course covers subjects which range from deterministic to stochastic methods and their possible application. More specifically, topics included are neural networks, finite state machine, decision trees, genetic algorithms, Bayesian techniques, inductive and reinforcement learning, and evolutionary programming.

During the exercises, the aim is to implement [i.e. apply] one or more of the topics introduced, possibly in an actual game. Some [if not all] of these exercises will be mandatory. 
Læringsaktiviteter:

One or two guest lectures will probably be given by people working for a game company. They work professionally with AI in games and their lectures will provide more insight in the actual applicability of such methods within game programming, making some of the concepts discussed during the course more tangible for the student.
-------------------------------
I introugen (mandag den 28. august til fredag den 1. september) er øvelsestimerne aflyst. Dvs. at der kun er undervisning fra 10-12.

Exercises have been cancelled during the intro week (Monday the 28th of August to Friday the 1st of September).That means you only have classes from 10AM-12.


Information om studiestruktur / Information about study structure
Dette kursus er en del af MTG-specialiseringen Spilprogrammering, som du kan finde beskrevet her:
MTG studiestruktur
For at blive cand.it. i MTG skal du bestå MTG¿s backbonekurser, og desuden gennemføre en 22,5 ECTS specialisering samt to 7,5 ECTS valgfag.

This course is part of the MTG specialization Game Programming ¿ find it described here:
MTG study structure
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.
 

Eksamensform og -beskrivelse:X. experimental examination form (7-scale; external exam), 13-skala, Ekstern censur

Some mandatory exercises.  

Litteratur udover forskningsartikler:Artificial Intelligence: A Modern Approach (2nd Edition) by Stuart J. Russell and Peter Norvig will be used primarily

 
 
Afholdelse (tid og sted)
Kurset afholdes på følgende tid og sted:
UgedagTidspunktForelæsning/ØvelserStedLokale
Mandag 10.00-12.00 Forelæsning ITU 3A18
Mandag 13.00-15.00 Øvelser ITU 3A50
Onsdag 10.00-12.00 Forelæsning ITU 3A18
Onsdag 13.00-15.00 Øvelser ITU 3A50

Eksamen afholdes på følgende tid og sted:
EksamensdatoTidspunktEksamenstypeStedLokale
2006-12-20 15:00 / 3PM Skriftlige arbejder ITU Eksamenskontoret / Exam Office
2007-01-22 Tidspunkt oplyses senere Mundtlig eksamen ITU Lokale oplyses senere
2007-01-23 Tidspunkt oplyses senere Mundtlig eksamen ITU Lokale oplyses senere