Pogamut : Genetic Bots

Genetic Bots


The Goal
To evolve behaviour of bot embodied in the game Unreal Tournament 2004 using genetic algorithms.

How to do it
First you have to have a framework that will enable you to perform thousands evaluations of bots' behaviour in reasonable time. For this purpose we have developed the Pogamut GRID. Application of genetic algorithms in this domain would be unimaginable without such cluster of Unreal Tournament servers.

Then you have to find the right decision structure to be evolved. I have decided to try:
  • Hierarchical decision trees evolved using Genetic programming
  • Neuroevolution

Full thesis text

Full text of the thesis can be downloaded here in PDF format.

Content of enclosed CD (thesis text included).


During the development I have also maintained this blog of the Genetic Bots Project.

Academic papers

  • Neural Bot - to my knowledge the first evolutionary in a FPS game (Quake2).
Non-evolutionary research on bots:

Created by: rudolf.kadlec. Last Modification: Saturday 30 of May, 2009 09:53:14 CEST by rudolf.kadlec.


Tiki RSS feed for weblogs

This work is supported by GA UK 1053/2007/A-INF/MFF (2007-8), GA UK 351/2006/A-INF/MFF (2006-8), the Ministry of Education of the Czech Republic (grant MSM0021620838) (2008-9), by the Program "Information Society" under project 1ET100300517 (2006-9), and the project Integration of IT Tools into Education of Humanities (2006-8) and by the project CZ.2.17/3.1.00/31162, which are financed by the European Social Fund, the state budget of the Czech Republic, and by the budget of Municipal House Prague.