CHAIR OF

COMPUTATIONAL

INTELLIGENCE

Information for the review of your exams (Klausureinsicht) of SS17 can be found here.

Description

This course addresses the basic and advanced topics in the area of computational intelligence and games. This course has three parts:

Part one addresses the basics in Evolutionary Game Theory (EGT). In this part you will learn about simple games such as scissors/rock/paper and the main focus on the strategies for playing games.

Part two is about learning agents and we focus on reinforcement learning mechanisms. There are three questions for games:

Part three contains the advanced topics in games and artificial intelligence such as how can we program an agent who can pass a Turing test? how can we consider physical constraints of a spaceship while moving in an unknown terrain? etc. 

This course will be held in English and is for Bachelor students. 

Master Students:

Please note that you must deliver an extra work as we discussed during the tutorials. More details to be announced here.

Lectures 

• Sanaz Mostaghim
• Alexander Dockhorn (Tutorials)

The lectures take place:   Thursdays 9:15-10:45 in G29 – 307

Slides

• Chapter 0: Organization
• Chapter 1: Introduction
• Chapter 2: Evolutionary Game Theory  
• Chapter 3: Introduction to Reinforcement Learning 
• Chapter 4: Dynamic Programming and Monte Carlo Method in RL 
• Chapter 5: Temporal Difference Learning
• Chapter 6: Monte Carlo Tree Search 
• Chapter 7: Rolling Horizon Evolutionary Algorithms
• Chapter 8: Multi-Objective Decision Making and Learning in Games
• Chapter 9: Procedural Content Generation (PCG)

• Scriptbook about RL 2014
• Scriptbook about RL 2016

Videos and simulations related to lectures

• Chapter 2: Hawk-Dove
• Chapter 2: Hawk-Dove-Worm
• Chapter 3: Link to MasterMind

Recorded Lectures

• Recordings can be found here: https://mediaweb.ovgu.de/Mediasite7/Catalog/catalogs/iks-cig
• Please note that you require your URZ account to be able to see the recordings. 

Tutorials 

• Group A: Mondays 9:15 - 10:45 in room G29 - K058
• Group B: Wednesday 9:15 - 10:45 in room G29 - 336
• Group C: Fridays 13:15 - 14:45 in room G29 - E037

The tutorials are scheduled as follows:

 Registration for the tutorials:

You should register for one of the groups A, B or C. If you have not yet registered for the tutorials, you must write an email to Alexander. 

Tutorial Slides and Assignments:

Instructions to the programming Assignment

Assignment 1: Chapter 2 - Evolutionary Game Theory 

Assignment 2: Chapter 2 & 3 - Game Policy  & Markov Decision Process & RL

Assignment 3: Chapter 4 & 5

Assignment 4: Chapter 6 & 7 - MCTS & Evolutionary Algorithms

Assignment 5: Chapter 8 - MOP and Hypervolumes

Assignment 6: Summary

Programming Assignment: 

All master students need to present their AI concept (pac-man and ghost) at at least one of the presentation exercise classes.  09./12./14.06. You don't need to show a prototype. We will just talk about your general idea. 

Deadline of the programming Assignment will be the 02.07. were you will need to hand in the final bots for pac-man (and ghosts in case you are a master student).

Please hand in your programming assignment by sending your documented source-code, neccessary
files for execution and a short explanation in written form to alexander.dockhorn@ovgu.de
In case you are working in a group list all the group members and including contact e-mail adresses
in your submission.

You will be notified about your successful submission in the following week.

Discussed Bot Examples

• RandomPacMan.java
• RandomJunctionPacMan.java
• MCTSAI Pacman.zip
• ExtendedGame.java

Past Exam:

Exam WS 2015/2016

Video References:

Flexible Muscle-Based Locomotion for Bipedal Creatures

Literature

• Nowak, Martin, Evolutionary dynamics : exploring the equations of life, Cambridge, Mass. [u.a.] : Belknap Press of Harvard Univ. Press , 2006 --> Link to OvGU Library
• 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
• T. L. Vincent and J. L. Brown, Evolutionary Game Theory, Natural Selection and Darwinian Dynamics, Cambridge University Press, 2012
• 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
• Kalyanmoy Deb, Multi-Objective Optimization using Evolutionary Algorithms, Wiley, 2001
• Literature about PCG: Paper1, Paper2, Paper3, Paper4
• Kruse, Borgelt, Klawonn, Moewes, Ruß, Steinbrecher, Computational Intelligence, Vieweg+Teubner, Wiesbaden, 2011
• Ines Gerdes, Frank Klawonn, Rudolf Kruse, Evolutionäre Algorithmen, Vieweg, Wiesbaden, 2004
• Zbigniew Michalewicz, Genetic Algorithms + Data Structures = Evolution Programs. Springer, Berlin, 1998