Priesterjahn

> (1) the complete title of one (or more) paper(s) published in the open 
> literature describing the work that the author claims describes a 
> human-competitive result,


Evolution of Human-Competitive Agents in Modern Computer Games

> (2) the name, complete physical mailing address, e-mail address, and 
> phone number of EACH author of EACH paper,


Steffen Priesterjahn
Department of Computer Science / Knowledge Based Systems Faculty of Electrical Engineering, Computer Science and Mathematics University of Paderborn
D-33095 Paderborn
E-Mail: spriesterjahn@uni-paderborn.de
Phone: ++49 (0)5251-60 3349
Fax: ++49 (0)5251-60 3338

Oliver Kramer
University of Dortmund
Department of Computer Science
Algorithm Engineering (Ls11)
44221 Dortmund
E-Mail:  oliver.kramer@cs.uni-dortmund.de
Phone: ++49 (0)231 - 755 7713

Alexander Weimer
Department of Computer Science / Knowledge Based Systems Faculty of Electrical Engineering, Computer Science and Mathematics University of Paderborn
D-33095 Paderborn
E-Mail: aweimer@uni-paderborn.de
Fax: ++49 (0)5251-60 3338

Dr. Andreas Goebels
University of Paderborn
Faculty of Electrical Engineering, Computer Science and Mathematics Computer Science Department
D-33095 Paderborn
E-Mail:   andreas.goebels@uni-paderborn.de
Phone:  ++49 (0)5251-60 3352
Fax:  ++49 (0)5251-60 3338

> (3) the name of the corresponding author (i.e., the author to whom 
> notices will be sent concerning the competition),


Steffen Priesterjahn

> (4) the abstract of the paper(s),


Modern computer games have become far more sophisticated than their ancestors. 
In this process the requirements to the intelligence of artificial gaming characters have become more and more complex. This paper describes an approach to evolve human-competitive artificial players for modern computer games. The agents are evolved from scratch and successfully learn how to survive and defend themselves in the game. Agents trained with standard evolution against a training partner and agents trained by coevolution are presented. Both types of agents were able to defeat or even to dominate the original agents supplied by the game. Furthermore, we have made a detailed analysis of the obtained results to gain more insight into the resulting agents.

> (5) a list containing one or more of the eight letters (A, B, C, D, E, 
> F, G, or H) that correspond to the criteria (see above) that the 
> author claims that the work satisfies,


G, H

> (6) a statement stating why the result satisfies the criteria that the 
> contestant claims (see the examples below as a guide to aid in 
> constructing this part of the submission),


G: The submitted work presents agents which were trained to compete in a commercial computer game. AI for computer games is complex and difficult because of the high dynamics and real-time nature of such games. Furthermore, the agents were trained from scratch beginning with fully random movements. No movement heuristics were used.

H: The evolved agents are able to outperform and dominate the orignal agents which were supplied by the game in every difficulty setting in close combat scenarios. They also evolved into very hard and almost unbeatable opponents for human players.

> (7) a full citation of the paper (that is, author names; publication 
> date; name of journal, conference, technical report, thesis, book, or 
> book chapter; name of editors, if applicable, of the journal or edited 
> book; publisher name; publisher city; page numbers, if applicable);
>

@InProceedings{ priesterjahn:2006,
  author = "S. Priesterjahn and O. Kramer and A. Weimer and A. Goebels",
  title = "{Evolution of Human-Competitive Agents in Modern Computer Games}",
  booktitle = "Proceedings of the IEEE Congress on Evolutionary Computation (CEC'06)",
  pages = "777--784",
  year = "2006",
  publisher = "IEEE Press"
}

> (8) a statement either that "any prize money, if any, is to be divided 
> equally among the co-authors" OR a specific percentage breakdown as to 
> how the prize money, if any, is to be divided among the co-authors; 
> and


Andreas hat vorgeschlagen erstmal etwas in der folgenden Art zu schreiben und falls wir etwas gewinnen dann darüber zu sprechen.

Steffen Priesterjahn  50%
Oliver Kramer         20%
Alexander Weimer      15%
Andreas Goebels       15%

> (9) a statement stating why the judges should consider the entry as "best"
> in comparison to other entries that may also be "human-competitive."


In contrast to other work in this area our agents had to start with a complete random movement. So, they had to adapt and learn how to set forward and sideward velocities, turn angle changes and when to attack from the scratch. 
By giving them such freedom, they could learn all possible behaviours without constraints by used heuristics. In spite of this increase in complexity the used evolution and environment model enabled the agents to solve this task in a fast and reliable way.