|Website:||website containing additional information|
|Period:||period 4 (week 17 through 27, i.e., 23-4-2012 through 6-7-2012; retake week 34)
|Participants:||up till now 35 subscriptions|
|Schedule:||Official schedule representation can be found in Osiris|
|Teachers:||Dit is een oud rooster!
|Contents:||Games like chess, checkers and go have been a (successful) object of study for Artificial Intelligence for a long time already. In video games like Quake and all Playstation or Xbox variants the use of AI techniques has been mainly limited to simple path planning for virtual characters. In this course we explore the more serious use of AI techniques for these video games, for instance in serious gaming and training. We investigate how the traditional central game control can be distributed over several independently operating agents controlling characters and/or parts of the environment. Of course we also investigate several path-planning techniques useful for computer games, and we describe dynamic re-planning algorithms useful for dealing with dynamic environments. Furthermore we discuss machine learning techniques such as evolutionary algorithms with neural networks to let agents learn their own behavior while playing game tournaments. We also discuss the importance of multi-agent cooperation and for this we discuss some game theory and solutions for cooperative team work.|
|Literature:||Instead of a single book we use a number of different articles that are discussed during the lectures. Slides of the lectures will be made available on the course webpage.|
|Course form:||Lectures by Jan Broersen or an invited lecturer. Also discussions based on papers pertaining to the previous lecture. The most important part of the course is formed by a programming assignment where groups of 3/4 students implement one of the discussed AI techniques in a computer game. Students have to come up with a proposal for adding AI to a computer game in a meaningful way. The proposal will be presented, discussed, evaluated and adapted if necessary. The end presentations include a demonstration of the AI-enhanced game.
|Exam form:||The final mark is determined by: Final Practical Project (70%) Participation (10%) Presentations (20%)|
|Minimum effort to qualify for 2nd chance exam:||Om aan de aanvullende toets te mogen meedoen moet de oorspronkelijke uitslag minstens 4 zijn.|
|Description:||Students are required to have the knowledge equivalent to the courses (1) Intelligent Agents, and (2) Adaptive Agents. Furthermore, practical experience with the computer language C++ is an advantage.|