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

61–70 of 113 posts

Re: Minecraft diamond challenge leaves AI creators stumped

#61

Post by gleenn »

semi-extrinsic wrote: post #56
YeGoblynQueenne wrote: post #23

Earlier quoted context omitted.

That's kind of the point. The trend in machine learning right now is to try and solve problems "from scratch" by training "end-to-end", which means without any prior knowledge. For example, DeepMind's last three or so iterations of their Alpha-X architecture for game playing did not even have any prior knowledge of the rules of the games they tackled (chess, shoggi, go and Atari games) and were trained entirely throu…

> The trend in machine learning right now is to try and solve problems "from scratch" by training "end-to-end", which means without any prior knowledge. In a strong sense, this implies ML is not "intelligent" in any conventional sense of the word. What little we have of understanding of learning and intelligence in the scope of humans strongly implies that drawing parallels with solutions to other tasks, building on…

Tranfer learning is a form of this, where you train the first half of a neural net over a huge set of data, then take a much more specific task and train just a bit more by adding some layers, and you get great sometimes industry leading results. Look up Google's BERT project, trained generically on English texts and then you can reuse that part in many different tasks like sentiment analysis or entity recognition or translation. An amazing way to leverage Googles compute and data access and do cool things even as a single developer.

Re: Minecraft diamond challenge leaves AI creators stumped

#62

Post by joe_the_user »

icebraining wrote: post #60
semi-extrinsic wrote: post #56

Earlier quoted context omitted.

> The trend in machine learning right now is to try and solve problems "from scratch" by training "end-to-end", which means without any prior knowledge. In a strong sense, this implies ML is not "intelligent" in any conventional sense of the word. What little we have of understanding of learning and intelligence in the scope of humans strongly implies that drawing parallels with solutions to other tasks, building on…

But they do build on previous knowledge (that's the training part), it's just the such knowledge is built from scratch, rather than taught by others.

A human can learn something through a fairly small amount of specific knowledge via written, verbal, etc instruction.

All the data and the training process together are very clunky in comparison.

IE, an inability to be taught by others is a serious limitation to say the least.

Re: Minecraft diamond challenge leaves AI creators stumped

#63

Post by semi-extrinsic »

icebraining wrote: post #60
semi-extrinsic wrote: post #56

Earlier quoted context omitted.

> The trend in machine learning right now is to try and solve problems "from scratch" by training "end-to-end", which means without any prior knowledge. In a strong sense, this implies ML is not "intelligent" in any conventional sense of the word. What little we have of understanding of learning and intelligence in the scope of humans strongly implies that drawing parallels with solutions to other tasks, building on…

But they do build on previous knowledge (that's the training part), it's just the such knowledge is built from scratch, rather than taught by others.

But it's not transferable. If you teach the AI to play checkers, you don't use that knowledge when trying to teach it chess.

Re: Minecraft diamond challenge leaves AI creators stumped

#64

Post by TulliusCicero »

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.…

> 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.

It's probably worthwhile to note that AlphaStar is trying to become as skilled as the strongest human players, whereas in this case it's more of a binary "is capable of getting diamonds" thing, they don't need to be world-class diamond miners.

Re: Minecraft diamond challenge leaves AI creators stumped

#65

Post by ben_w »

joe_the_user wrote: post #62
icebraining wrote: post #60

Earlier quoted context omitted.

But they do build on previous knowledge (that's the training part), it's just the such knowledge is built from scratch, rather than taught by others.

A human can learn something through a fairly small amount of specific knowledge via written, verbal, etc instruction. All the data and the training process together are very clunky in comparison. IE, an inability to be taught by others is a serious limitation to say the least.

Perhaps we can learn from small data, perhaps that’s an illusion. How much of our mind is hard-wired by our genes, our genes being a very slow-learning form of intelligence?

Or, when we see “one” example of a new animal (for example), do we see a single picture? Or do we see it moving for about a second? Effectively multiple images? And, having previously learned a general model for physics, stereoscopic vision, and lighting, does that one second of motion gives us the size, shape, and a guess at the musculature of the animal?

If you strip those advantages, how many training examples do we need? The examples of people blind from birth or from extreme youth who regain vision in adulthood[0] implies that we learn a lot in our youth about how to see, which we can share between recognition tasks we learn later. Keeping those basic skills — avoiding “catastrophic forgetting” — still seems to be a rare and advanced feature in AI, but it’s not impossible.

There is still a lot we don’t know about how our own minds work. We might be closer than we realise, or much further.

[0] https://en.m.wikipedia.org/wiki/Mike_May_(skier) amongst others. I never did find the name of the guy who learned to see from touching a monkey statue…

Re: Minecraft diamond challenge leaves AI creators stumped

#66

Post by Buttons840 »

Y'all got any of them AIs for turned based strategy games?

Seriously, I'm starting to think turn based strategy games like Civilization, etc, will be the last to get any attention. Why? We need good AIs for these games and they're not yet solved as far as I know. Furthermore, you don't have to model the human interface by limiting actions per second like with DotA or StarCraft. Yes, we solved Go, but turn based strategy games on PC are more complicated. Seems like a worthy area to research.

Does anyone know of any work on games like these?

Re: Minecraft diamond challenge leaves AI creators stumped

#67

Post by gcpwnd »

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…

Now we just deny the prophecies of the upcoming singularity?

Re: Minecraft diamond challenge leaves AI creators stumped

#69

Post by CydeWeys »

asdfman123 wrote: post #39
CydeWeys wrote: post #2

Interestingly, when I started playing the game, this task was essentially impossible for human players without consulting external resources, because the crafting recipes were unlisted , and you needed to know the specific recipes for various things like crafting tables, pick-axes, and shovels that would be nearly impossible to discover by randomly trying to guess recipes. I don't know if there's a starting tutorial…

Minecraft was hugely successful early on specifically because it didn't have to explain itself -- you had to do your research to figure out the game. And when you died you sometimes lost everything. I guess they needed to add tutorials to better accomodate the wave of younger people who picked up the game in the mid 10's, but I actually appreciate Notch's decisions (or series of happy accidents that culminated in a h…

It really did have to explain itself though. It was frustrating trying to play without spoilers because it was basically impossible. You had to go read guides saying how to make a crafting table, how to make tools, etc.

Re: Minecraft diamond challenge leaves AI creators stumped

#70

Post by Iv »

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 like the constraints they put. But realistically, if you want to mimick the way humans learn, you want to put in place some kind of transfer learning: You have a model that has already been trained to understand video frames, maybe has played a few video games before. Then, 60M frames of minetest can be used to understand things about the game.

But also, the machine learning algorithms we have nowadays are in many ways superhuman. Seeing how much can be learned with these constraints is interesting as well.

Post reply on HN