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

101–110 of 113 posts

Re: Minecraft diamond challenge leaves AI creators stumped

#101

Post by TheRealPomax »

allovernow wrote: post #50
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.

Not really, no. Procesing and recording data is not "learning". Machines are incredibly much faster at _classifying_ but that's been our problem for decades now: we figured out how to make insanely efficient and unreasonably good classifiers. However, we haven't been really able to turn that into efficient "learning", the best we've been able to do is what Deep Mind does, which requires very power machines working with literally decades worth of data.

Re: Minecraft diamond challenge leaves AI creators stumped

#102

Post by raducu »

bitL wrote: post #96
gleenn wrote: post #61

Earlier quoted context omitted.

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…

> as a single developer I think you are out of luck already. Even with transfer learning, retraining BERT to fit a larger dataset takes ages even on an RTX 8000. A single state-of-art experiment/training run at Facebook now costs 7 figures. The age of individual SOTA ML researcher/developer is over.

This is so sad, actually, and It's not just ML, it is every kind of new tech and discovery.

To me it shows we have already picked the easy fruits and technology will not continue to evolve exponentially.

Re: Minecraft diamond challenge leaves AI creators stumped

#103

Post by ars »

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

You misread it. It's around 300 hours of training data. It's 4 days to absorb those 300 hours.

I bet a human child who has never even seen a computer could learn to do this in far less than 300 hours. I suspect even 1 hour would be enough.

Re: Minecraft diamond challenge leaves AI creators stumped

#104

Post by sailingparrot »

catalogia wrote: post #79
sailingparrot wrote: post #76

Earlier quoted context omitted.

> A good AI for a game like Civilization would have knowledge of human social concepts like honor and vindictiveness, This is a pretty wild assumption to say the least.

I'm very curious why you're so skeptical of this. The AI that was created for the Civilization games did in fact try to model these and similar aspects of human behavior, with the intent of creating AIs that played in ways humans would consider natural or fitting. They named the AIs after historical humans and tried to make the AIs act in ways that would be perceived as similar to their namesakes. Nuke-happy Gandhi w…

An AI can act in any way you want without having 'knowledge' of human concepts. AlphaStar can play in a variety of style, from defensive to very agressive, and yet has no understanding of concepts or values.

Re: Minecraft diamond challenge leaves AI creators stumped

#105

Post by catalogia »

sailingparrot wrote: post #104
catalogia wrote: post #79

Earlier quoted context omitted.

I'm very curious why you're so skeptical of this. The AI that was created for the Civilization games did in fact try to model these and similar aspects of human behavior, with the intent of creating AIs that played in ways humans would consider natural or fitting. They named the AIs after historical humans and tried to make the AIs act in ways that would be perceived as similar to their namesakes. Nuke-happy Gandhi w…

An AI can act in any way you want without having 'knowledge' of human concepts. AlphaStar can play in a variety of style, from defensive to very agressive, and yet has no understanding of concepts or values.

I think I see the issue, 'knowledge' and 'understanding' are loaded terms. The AI needs to behave as though it understands these things [if it's to be fun], but does not need to in fact 'understand' or 'know' these things.

Re: Minecraft diamond challenge leaves AI creators stumped

#106

Post by catalogia »

oefrha wrote: post #86
catalogia wrote: post #84

Earlier quoted context omitted.

The problem is that not all combinations of those traits are equally valid, and the optimal distributions of those traits are ill defined. If warmongering is some number 0 to 1, with 0 being Gandhi and 1 being Genghis Khan, that's all fine and good. But what does the distribution curve of a randomly generated nation leader look like and how well does that curve conform to the expectations and perceptions of the playe…

> As for tactical AI (which is only one component of Civilization), an optimal play from the AI probably isn't what most players desire, nor is optimal play with randomly imposed inefficiencies. No one's demanding optimal play from AI. Meanwhile I'm sure pretty much no one's happy with idiotic AI, which is what we have at the moment. I already gave an example: "smashing waves and waves of units into a walled city wit…

Making an AI that avoids engagements with unwinnable odds is fine and all, but I would expect that to be a relatively simple matter that doesn't flex the strengths of modern approaches to AI. In fact looking back on my extensive albeit dated experience playing Civ2, I'm pretty sure the AI does in fact prefer engagements in which the odds favor it. If anything, the biggest gripe I had with it is the AI would often employ sound but tedious tactics, moving several dozen units per turn which, although not forbidden by the rules, isn't a lot of fun for the human to wait through. That is a trickier matter, since some humans do in fact play like that, so perhaps the AI should when the human does, but shouldn't when the human doesn't.

I don't think difficulty in analyzing the odds of engagements like that is the reason good AI for Civilization is elusive.

Re: Minecraft diamond challenge leaves AI creators stumped

#107

Post by catalogia »

sullyj3 wrote: post #87
catalogia wrote: post #71

Earlier quoted context omitted.

> Seriously, I'm starting to think turn based strategy games like Civilization, etc, will be the last to get any attention. Why? I don't think the answer is technical. A good AI for a game like Civilization would have knowledge of human social concepts like honor and vindictiveness, which are both concepts problematic to pin down. The definitions of concepts like these are fluid, they change with the times and societ…

> if you're shooting for human-like behavior You're not though, you're just trying to build a bot that can win the game.

Not if you want a fun game. Civilization is a game about role-playing as the leader of a nation, not merely about sprinting to the finish. The AI is meant to take part in that roleplaying, to enhance the experience for the player. An AI that consistently loses but does so in a very human way is better than an AI that consistently wins but plays like a machine.

(Obviously the ideal is an AI that plays like a human and can hold its own, but a playstyle similar to humans is definitely more important than ability to win.)

Re: Minecraft diamond challenge leaves AI creators stumped

#108

Post by ramblerman »

imtringued wrote: post #27
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. That's not a very useful goal. I can trivially make a game that is impossible for such an AI to win. It would require you to enter a 1024 bit code [0] and if you are correct you win. For a speed runner the time it takes to beat the game is merely limited by their typi…

You are confusing the goal and the method.

Setting up a stupid method of getting to the goal doesn't disqualify said goal.

Re: Minecraft diamond challenge leaves AI creators stumped

#109

Post by sailingparrot »

catalogia wrote: post #105
sailingparrot wrote: post #104

Earlier quoted context omitted.

An AI can act in any way you want without having 'knowledge' of human concepts. AlphaStar can play in a variety of style, from defensive to very agressive, and yet has no understanding of concepts or values.

I think I see the issue, 'knowledge' and 'understanding' are loaded terms. The AI needs to behave as though it understands these things [if it's to be fun], but does not need to in fact 'understand' or 'know' these things.

Exactly yes.

Re: Minecraft diamond challenge leaves AI creators stumped

#110

Post by Buttons840 »

catalogia wrote: post #107
sullyj3 wrote: post #87

Earlier quoted context omitted.

> if you're shooting for human-like behavior You're not though, you're just trying to build a bot that can win the game.

Not if you want a fun game. Civilization is a game about role-playing as the leader of a nation, not merely about sprinting to the finish. The AI is meant to take part in that roleplaying, to enhance the experience for the player. An AI that consistently loses but does so in a very human way is better than an AI that consistently wins but plays like a machine. (Obviously the ideal is an AI that plays like a human and…

I disagree and have a hard time enjoying opponents that I know are cheating to enable thmselves to compete.

After I learned the basics my own opinion is that Civilization is no longer a fun game, due to the poor AI.

We can probably agree that finding fun and interesting ways to dumb down an AI will be a cool area for research and new ideas in the future, but we need strong AI before we can figure out fun ways to weaken it.

Post reply on HN