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

51–60 of 113 posts

Re: Minecraft diamond challenge leaves AI creators stumped

#51

Post by codegladiator »

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…

> with only 4 days of training data

so 4 days to train their AI and not 4 days of training data.. on the data which was "60 million frames of recorded human player data"

Re: Minecraft diamond challenge leaves AI creators stumped

#52

Post by johnmoberg »

progval wrote: post #37
johnmoberg wrote: post #33

Earlier quoted context omitted.

The challenge was to accomplish this without domain knowledge... if you can do this with GOFAI, please go ahead and shock the world.

You have to use at least some domain knowledge, else you would be making a general-purpose artificial intelligence. The rules actually say: "without relying heavily on human domain knowledge" (emphasis mine). The rule is actually quite vague, which is not very surprising, as it seems quite hard to define what domain knowledge is allowed and what isn't without having lots of loopholes.

I agree that is vague. But there are plenty of RL algorithms that learn with essentially no domain knowledge, e.g., MuZero[1] which doesn't even use a model. That doesn't make it AGI -- it only masters a single game at a time and we currently don't know how to transfer that knowledge to other domains.

[1] https://arxiv.org/abs/1911.08265

Re: Minecraft diamond challenge leaves AI creators stumped

#54

Post by detaro »

faissaloo wrote: post #53

Minecraft is a game that is played by consulting manuals and learning from others, I would be astonished if an AI could magically discover how to find diamonds.

Fairly sure a human would "magically" figure it out with the 11 days of gameplay footage the AI got ;)

Re: Minecraft diamond challenge leaves AI creators stumped

#56

Post by semi-extrinsic »

YeGoblynQueenne wrote: post #23
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…

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 previous knowledge, is the key to intelligence.

Perhaps the purest expression of this is in pedagogy of math. Piaget and Brissiaud are some of the scholars who I think really grokked this. They brought forward the concept of compression as essential for learning. E.g. if you have learned but not yet compressed the operation of addition, you will have a very hard time learning multiplication. After addition has been compressed such that you don't have to spend any effort doing it, you are ready to learn multiplication.

Maybe it would be worthwile to explore if there are AI techniques that can learn simple tasks first, then use that knowledge to solve harder tasks?

Re: Minecraft diamond challenge leaves AI creators stumped

#57

Post by moomin »

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 ?

The resources the programs can use are well specified. A human child is not part of the specified equipment.

Re: Minecraft diamond challenge leaves AI creators stumped

#58

Post by pishpash »

chmod775 wrote: post #40
Jasper_ wrote: post #28

Earlier quoted context omitted.

What if you had 22 hours of footage showing speedrunners entering the 1024 bit code to train on?

It would be possible to do that, but it's not really what was asked. The way you'd train a neural network with that footage is comparing the recording of the neural network playing the game to the recording of the speedrunner, and scoring it based on the difference in the footage. However it wouldn't really be learning "from scratch" and "end-to-end" anymore, since you're essentially teaching it to imitate and play l…

How about it watches how the human obtains the secret number (1024) in this game, then next time extrapolates the process to a different game with a different secret number? That is the kind of learning that humans do and AI's can conceivably do the same.

Re: Minecraft diamond challenge leaves AI creators stumped

#59

Post by chmod775 »

pishpash wrote: post #58
chmod775 wrote: post #40

Earlier quoted context omitted.

It would be possible to do that, but it's not really what was asked. The way you'd train a neural network with that footage is comparing the recording of the neural network playing the game to the recording of the speedrunner, and scoring it based on the difference in the footage. However it wouldn't really be learning "from scratch" and "end-to-end" anymore, since you're essentially teaching it to imitate and play l…

How about it watches how the human obtains the secret number (1024) in this game, then next time extrapolates the process to a different game with a different secret number? That is the kind of learning that humans do and AI's can conceivably do the same.

That's just not how neural networks learn. They generally can't "watch" others to learn.

In the example above, at no point the neural network would be watching the video footage. The reference footage is just used for (automatically) scoring how well it does during training. It's not fed into the network itself in any shape or form.

Re: Minecraft diamond challenge leaves AI creators stumped

#60

Post by icebraining »

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…

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.
Post reply on HN