AI Challenge: Ants - Post Mortem

D_Alex

Late last year a LessWrong team was being mooted for the Google AI challenge (http://aichallenge.org/; http://lesswrong.com/r/discussion/lw/8ay/ai_challenge_ants/). Sadly, after a brief burst of activity, no "official" LessWrong entry appeared (AFAICT, and please let me know if I am mistaken). The best individual effort from this site's regulars (AFAICT) came from lavalamp, who finished around #300.

This is a pity. This was an opportunity to achieve, or at least have a go at, a bunch of worthwhile things, including development of methods of cooperation between site members, gathering positive publicity, and yes, even advancing the understanding of AI related issues.

So - how can things be improved for the next AI challenge (which I think is about 6 months away)?

The Ants problem -- if I'm understanding it correctly -- is a problem of coordinated action.

One of the interesting aspects of the winning entry post-mortem is the description of how dumb and how local the basic strategy the winner used:

There’s been a lot of talking about overall strategies. Unfortunately, i don’t really have one. I do not make decisions based on the number of ants i have or the size of my territory, my bot does not play different when it’s losing or winning, it does not even know that. I also never look which turn it is, in the first turn everything is done exactly the same as in the 999th turn. I treat all enemies the same, even in combat situations and i don’t save any hill locations.

Other than moving ants away from my hills via missions, every move i make depends entirely on the local environment of the ant.

Interesting reading, overall.

EDIT: Another example of overthinking it: http://lesswrong.com/lw/8ay/ai_challenge_ants/56ug One wonders if the winner could understand even half those links.

Yes, the write-up is very interesting. But while the strategy was very local, he did end up having mechanisms for coordinating action between ants with otherwise pretty simple decision rules, especially for combat. At least, that's the way it looks to me. Did you mean for your comment to be a criticism of what I wrote? If so, could you say a bit more?

1malthrin14y

Agreed. We can certainly do better than that. Unless I have a major life-event before the next AI challenge, I'll enter and get the LW community involved in the effort.