Advanced Programming in Computational Intelligence in Games

Summer

(in German: Advanced Programming in Computational Intelligence in Games )

Module-ID: FIN-INF-120495

Abbreviation AP-CIG

Credit Points 6

Semester Summer

Term starting at 1.

Duration 1 Semester

Language english

Level Master

Link:	LSF
Limited accessability:
Responsibility:	Sanaz Mostaghim
Lecturer:	Sanaz Mostaghim
Classes:	Lecture Advanced Programming in Computational Intelligence in Games Tutorials Advanced Programming in Computational Intelligence in Games
Applicability in curriculum:	- M.Sc. INF: Informatik - M.Sc. INGINF: Informatik - M.Sc. WIF: Informatik - M.Sc. DKE: Applied Data Science - M.Sc. VC: Computer Science

Intended learning outcomes:
Students ...

• carry out a large programming project using the concepts from the theoretical part of the course.
• have a full understanding of the algorithms of computational Intelligence in Games.
• learn to develop new ideas and apply them to new problems in the context of AI and Games.
• learn to program the methodologies from the lectures in teams.

Content:
This course addresses the basic and advanced topics in the area of computational intelligence and games and contains three parts: Part 1 addresses the basics in Evolutionary Game Theory (EGT). In this part you will learn about simple games such as scissors/rock/paper and the focus on the strategies for playing games. Part 2 is about learning agents, and we focus on reinforcement learning mechanisms. There are three questions for games:

• How can we use the information from a search mechanism to learn?
• How can we use reinforcement learning to find for a better strategy?
• How can we use reinforcement learning as a search mechanism?

The application is on board games. Part 3 contains the advanced topics in games and artificial intelligence How can we consider physical constraints of a spaceship while moving in an unknown terrain. Other topics are Monte Carlo Tree Search, Procedural Content Generation, Decision Making and Multi-Objective Learning.

Workload:
56 contact hours + 94h self study

Pre-examination requirements:	Type of examination:	Teaching method / lecture hours per week (SWS):
	Hausarbeit (home work containing programming) Exercises and Tutorials Klausur (written Exam) 120 Minuten	lectures (2 SWS) exercise classes (2 SWS)

Prerequisites according to examination regulations:	Recommended prerequisites:
none	Programming experience

Media:

Literature:

­Ian Millington and John Funge, Artificial Intelligence for Games, CRC Press, 2009 Richard S. Sutton and Andrew G. Barto, Reinforcement Learning: An Introduction, MIT Press, Cambridge, MA, 1998 Jorgen W. Weibull, Evolutionary Game Theory, MIT Press, 1997 Thomas Vincent, Evolutionary Game Theory, Natural Selection, and Darwinian Dynamics, Cambridge University Press, 2005 Josef Hofbauer, Karl Sigmund, Evolutionary Games and Population Dynamics, Cambridge University Press, 1998

Comments: