Gamasutra: The Art & Business of Making Gamesspacer
View All     RSS
October 23, 2014
arrowPress Releases
October 23, 2014
PR Newswire
View All
View All     Submit Event

If you enjoy reading this site, you might also want to check out these UBM Tech sites:

The StarCraft AI Competition
by Ben Weber on 02/04/11 09:59:00 pm   Featured Blogs

The following blog post, unless otherwise noted, was written by a member of Gamasutra’s community.
The thoughts and opinions expressed are those of the writer and not Gamasutra or its parent company.


I have been involved in research in RTS games for a few years now. One of the things that really caught my attention was that most researchers from an AI background were unable to apply their work to the complexity of current generation RTS games. Instead, they would use an abstract RTS game and evaulate their work in their restricted framework. But I had a different agenda. My goal was to learn from expert players, from expert replays, and therefore I required dealing with the complexity of a complete game. 

To settle the score of which AI technique worked best for RTS games,  I proposed a competition, in which bots compete in a heads-up tournament for the winning position. I wanted to simulate an environment in which bots were placed in a situation as close to professional gaming as possible. The result was the AIIDE 2010 StarCraft AI Competition.

AIIDE 2010 StarCraft AI Competition

This was an international event, involving a dozen countries. The task given to participants was to build the best performing bot for AI vs AI matches in a double elimination tournament bracket. The competition included four different tournaments which involved varying levels of complexity, but the most popular mode by far was the complete gameplay tournament. This mode simulated a professional StarCraft tournament, such as BlizzCon, but for bots. In all, 28 participants submitted bots for the tournament. 

The competition was open to everybody, but most of the participants were affiliated with a university. Non-affiliated participants included both hobbyist programmers and industry veterans. Of the university affiliated participants, it was quite remarkable to see how many non-games related participants used the event to justify the study of game AI. In particular, UC Berkely participants were able to convince their advisor that StarCraft was an intestesting domain even though their focus was NLP (Natural Language Processing).

UC Berkeley ended up winning the competition with an interesting strategy that focused on air units. But it is not a dominant strategy and there is still a lot of potential for AI techniques to be employed in this domain. During play testing with a former pro-gamer, it was shown that the bot is not yet at expert level, even though it can defeat most casual gamers. 

UC Berkeley Winners (Left) and Organizer (src: Vadim Bulitko)

The competition was unique in that it required AI systems to work at the same level as gamers. That is, the AI has to operate with imperect information and scout the opponent due to the fog of war. The results of the first competition were a huge success, and players are looking forward to playing a more sofistacated AI system. 

The competition was made possible by the BWAPI project, which provides hooks into StarCraft (Blizzard provided a content-use license for the day of the competition). While the game is over 10 years old, it is still an active game and players are enjoying the new gameplay experience provided by AI systems.

Should more games expose their API for research? The StarCraft competition will continue in 2011 and gamers are looking forward to the challenges provided by research in this domain. 

Related Jobs

Avalanche Studios
Avalanche Studios — New York, New York, United States

UI Programmer
Avalanche Studios
Avalanche Studios — New York, New York, United States

UI Artist/Designer — Hunt Valley, Maryland, United States

Lead UI Engineer — Chicago, Illinois, United States

Lead UI Engineer


Ryan Andonian
profile image
That's funny how an abnormal strategy won. I don't play much SC, but in most other RTS games, air units are only supplementary units, not the main combat force (except, of course, USA Air General from CnC Generals). But I guess that only proves how important adapting to information is when it comes to AI systems, and how initial planning isn't the only thing that needs to go into forming strategies. Not like that's an easy thing to implement.

PS: I dig your shirt

Albert Meranda
profile image
Very cool. The Ars Technica article is great.

David Hughes
profile image
I second that. I know next to nothing about Starcraft, but I've always loved AI design.

John Trauger
profile image
It makes sense.

The programmers were playing their opponents not playing against them. They built a strategy which may not have won on muscle or tactical acumen, but won by throwing the other AIs a curve they weren't expecting and couldn't cope with.

Jesse Crafts-Finch
profile image
Seems more like ranked starcraft players weren't able to cope with it either.

The major reason Starcraft players tend to not use Mutalisks as primary combat units is that they are extremely difficult to micri-manage in a way that prevents them from clumping AND allows them to do significant damage; a problem which the AI seems to have been able to deal with.