Winner of 2011 Google AI Challenge Describes Released Code • Hacker News Board

Re: Winner of 2011 Google AI Challenge Describes Released Code

#21

Post by tvorryn » Sat, Dec 24, 2011, 7:54 PM UTC

cpeterso wrote: post #18

DanBC wrote: post #17

I see a few people saying that they didn't have much time (or that they didn't want to spend too much time) for this. Is that really actually true, or is it some kind of 'modesty'[1]? When people talk about IQ there's usually a list of people saying something like "IQ is meaningless, it's a flawed concept (but my IQ is 138)". Are there any people saying "I worked really hard at this, I spent a lot of time and effort.…

Netlix's movie rating prediction contest is a great example of smart teams collaborating. As the contest progressed some teams would join forces forming new hybrid algorithms.

Yeah. In this competition collaboration was discouraged. That does keep politics/alliance building skills out of the equation at the cost of worse overall final products.

Re: Winner of 2011 Google AI Challenge Describes Released Code

#22

Post by peregrine » Sat, Dec 24, 2011, 8:42 PM UTC

Jyaif wrote: post #19

peregrine wrote: post #3

Now this is what I go to HN for! The most interesting part for me was that he did not focus on some huge strategy. Just individuals and small groups with clear goals and constant revaluation. Keeping in mind that the only thing kept between rounds were missions and those were constantly reevaluated as well. I think this is a vivid, albeit simplified, example of how successful organizations of anything should operate.…

What's that? You aren't more interested in the SOPA drama?

Well I was when it was 1 day from being jammed down our throats. Then it was postponed to the new year, at least the lobbyists in our courts(EFF, Google, etc) have sometime to throw some cash around. And people can do something.

I do think the SOPA Drama was a bit delayed and overblown here on HN.

Re: Winner of 2011 Google AI Challenge Describes Released Code

#23

Post by scotty79 » Mon, Dec 26, 2011, 12:38 PM UTC

> Otherwise if the ant was just spawned sitting on my hill, the target border tile is determined using some complex calculation considering the ratio of own/enemy ants near that border position, the possible distance to enemy hills, how many ants are already on a mission to a near border tile and how long they do need to reach their desitnation... Oh, I'm kidding, it was random. Completely random. Like in target = area.border.get(turnRandom.nextInt(area.border.size()));

Nice pun targeted at over-thinking of things. If you try to take many things into account without any concrete knowledge of how they influence outcome you'll get random result. So you may just start with random and see if it's good enough.