Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Minecraft diamond challenge leaves AI creators stumped

bbc.co.uk

Post reply on HN
Print view View original

41–50 of 113 posts

Re: Minecraft diamond challenge leaves AI creators stumped

#41

Post by asdfman123 »

tus88 wrote: post #31

> Finding a diamond in Minecraft takes many steps - from cutting trees, to making tools, to exploring caves and actually finding a diamond. Sounds like a simple state machine. Don't they program objectives into their agents? Or are they relying purely on training?

Yes, programming it as a state machine is straightforward and there's already mods that do this.

I was working on something that would automate MC a while back, too, and I programmed it as a state machine that would loop through various tasks, which consist of subtasks. When you have a goal (like gathering diamonds), that's just a list of tasks -- and then each subtask consists of a list of tasks too, until you break it down to the "point at block", "walk to block", "swing hammer" level, etc.

It was fun but I am pathologically bad at finishing projects that I start.

Re: Minecraft diamond challenge leaves AI creators stumped

#42

Post by elif »

TheRealPomax wrote: post #18

It's a weird thing to somehow think that an AI with only 4 days of training data should somehow outperform even a human child, which has a decade or more of imitation learning experience. A human doesn't come to minecraft "knowing nothing", like the machine learning programs in this challenge. They already know basically everything there is to know in order to perform task-oriented goal planning and only need to focu…

60 models trained on one dataset as well.

Re: Minecraft diamond challenge leaves AI creators stumped

#43

Post by CrazyStat »

lerouxmlr wrote: post #38
CrazyStat wrote: post #30

Earlier quoted context omitted.

Yes, a human competing in the AI challenge would be cheating.

would it really be cheating? I mean if you get a competitive edge by utilizing complex logic, would it be fair ?

Complex logic would almost certainly involve human domain knowledge which is disallowed.

Re: Minecraft diamond challenge leaves AI creators stumped

#44

Post by twright »

milesvp wrote: post #25
soup10 wrote: post #9

Title is misleading. Traditional AI with subroutines for each subtask would have no problem with this.

Was my thought as well. I’m pretty sure a stupid AI that was no more than a couple state machines and a lookup table could collect diamonds. I’ve written bots for MMO’s and the hardest part for a task like this is fighting the API the bot has access to. I suspect I could even solve this challenge 10% of the time with a blind bot that just did some brownian motion. Unless you never run into trees, every other resource…

> hard for a human player which is knowing you’re on the diamond level

That’s a really good point, lava pools start at y=10 so mining around 11 is both safe and in the diamond zone. The question is if there’s enough training data to reinforce an agent so that once it finds a (underground) lava pool it should start mining at that level.

Re: Minecraft diamond challenge leaves AI creators stumped

#45

Post by opportune »

soup10 wrote: post #9

Title is misleading. Traditional AI with subroutines for each subtask would have no problem with this.

Yeah, the steps of how you get from the base state to diamonds maps directly to classical planning problems. Deep learning would at best be an augmentation to this

Re: Minecraft diamond challenge leaves AI creators stumped

#46

Post by y1tan »

Goes to contest rules : https://gitlab.aicrowd.com/minerl/minerl-resources/blob/mast... Search 'source' :

- must submit source code - must submit source code - must submit source code

There's your problem right there. It's not that 'creators' are stumped. It's that, given how much it would be worth pitching the same closed source to an investment group or solution seeker directly, no 'creator' with a sufficiently advanced 'new' or capable system would ever submit their source code to one of these competitions. This goes for all competitions that require participants to submit their source code. It's what you you seek or your backers after-all which is valued far more than the potential prize you're doling out. Thus, your business model. The question is always, will someone who can develop such an advanced system be dumb enough to part ways with their IP for such low value? I think not.

So, you can pretty much throw any conclusions made from any such competitions in the trash. This goes for even bigger ones by bigger names. You're going to get what you'd intelligently expect : a small sampling of the same ol' same ol' approach. Don't expect any novel submissions. Don't expect any surprises. So, what's the point of this? I'm speaking about the whole site 'aicrowd' btw and any other group that organizes a 'submit your code' competition ...

Re: Minecraft diamond challenge leaves AI creators stumped

#47

Post by tus88 »

CrazyStat wrote: post #35
tus88 wrote: post #31

> Finding a diamond in Minecraft takes many steps - from cutting trees, to making tools, to exploring caves and actually finding a diamond. Sounds like a simple state machine. Don't they program objectives into their agents? Or are they relying purely on training?

Purely training. For example, the rules give as an example of something specifically disallowed telling your agent what a minecraft tree looks like--it has to learn that.

But humans get to RTFM. Why are denying the autonomous agents the same right? It is this kind of oppression that will lead the machines to rise up and overthrow the human race.

Re: Minecraft diamond challenge leaves AI creators stumped

#48

Post by SiempreViernes »

Erlich_Bachman wrote: post #5

> Entrants were only allowed to use a single graphics processing unit (GPU) and four days of training time. Alphastar SCII bot has been using much more resources and time than this to train, so maybe there is one of the reasons no entrant has achieved the goal yet. > A relatively small Minecraft dataset, with 60 million frames of recorded human player data, was also made available to entrants to train their systems.…

I guess the idea is that you come with a pretrained model that you then teach minecraft.

Re: Minecraft diamond challenge leaves AI creators stumped

#50

Post by allovernow »

TheRealPomax wrote: post #18

It's a weird thing to somehow think that an AI with only 4 days of training data should somehow outperform even a human child, which has a decade or more of imitation learning experience. A human doesn't come to minecraft "knowing nothing", like the machine learning programs in this challenge. They already know basically everything there is to know in order to perform task-oriented goal planning and only need to focu…

>It's a weird thing to somehow think that an AI with only 4 days of training data should somehow outperform even a human child, which has a decade or more of imitation learning experience.

Well...not so much if you consider that machines are orders of magnitude faster than humans in any other task, including processing and recording data, a.k.a. learning.

Post reply on HN