Computational Intelligence - Computational Intelligence in Games

Computational Intelligence in Games - SS 2015

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:

– How can we use the information from a search mechanism to learn?

– How can we use reinforcement learning to find a better strategy?

– How can we use reinforcement learning as a search mechanism?

The application is on board 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.

Lectures

Lecturer: Sanaz Mostaghim
Teaching assistant: Xenija Neufeld

+++++++ Exam will be on Friday 17.07.2015 at 12 - 14 in room G29-307 +++++++

The lectures take place: Wednesdays 9:15-10:45 in G29 – 037 (in Ground Floor)

Slides

Chapter 0: Organization
Chapter 1: Introduction
Chapter 2: Evolutionary Game Theory
Chapter 3: Introduction to Reinforcement Learning (Updated on May 12th)
Chapter 4: Dynamic Programming and Monte Carlo Method in RL
Scriptbook about RL (password access and only for the students of Otto von Guericke University Magdeburg)
Chapter 5: Temporal Difference Learning
Chapter 6: Monte Carlo Tree Search
Chapter 7: Physical Traveling Salesman Problem and Rolling Horizon Evolutionary Algorithms
Chapter 8: Multi-Objective Learning in Games
Chapter 9: Procedural Content Generation and CIG Research

Videos and simulations related to lectures

Chapter 2: Hawk-Dove
Chapter 2: Hawk-Dove-Worm
Chapter 7: Codes related to Physical Traveling Saleman Problem (PTSP)

Recorded Lectures

Tutorials

The next tutorial will be on Tuesday 29.06.2015.

Location and time: Tuesdays G29 - 037 at 15:15.

Assignments

Chapter 2 - Solutions
Chapter 3 and 4 - Solutions
Chapter 4 and 5 - Solutions
Chapter 6 and 7 - Solutions
Chapter 8 - Solutions

Master Students:

Please note that you must deliver an extra work as we discussed during the tutorials. There will be two presentation days, on which you must present your work on the Fighting Game:

Tuesday 09.06.2015: Presentation of maximal 5 slides
Tuesday 07.07.2015: Final Presentations

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
and to be completed