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

21–30 of 113 posts

Re: Minecraft diamond challenge leaves AI creators stumped

#21

Post by willis936 »

SquareWheel wrote: post #17
willis936 wrote: post #8

Earlier quoted context omitted.

If the challenge was to train an AI to be able to read a recipe book that would be more impressive imo. Even more impressive would be an AI that could gather the necessary resources. It would be a full game playing AI. An imitation AI to get diamonds is neat, but the fact that it is considered feasible on one GPU in one day speaks to the difficulty of the problem more than anything imo.

It may be cheating, and sort of against the point, but those recipes are stored as json files. Makes things a lot easier.

Allowing access to the data changes the problem. It’s an interesting problem in its own right, but seems much easier to accomplish and arguably much less valuable than limiting input to images and output to mouse/keyboard. Teaching computers to interact with the world is the trick that we want to teach.

Re: Minecraft diamond challenge leaves AI creators stumped

#22

Post by simias »

I'm a bit surprised that anybody is surprised by this lack of success, that seems like a hugely complicated task given the limited amount of time and resources. The amount of possible scenarios the AI needs to be able to handle (fall damage, environmental hazards, block types behaving differently, lighting, day/night cycles and of course enemies) plus the extremely open-ended gameplay where you can almost always dig in every possible direction while collecting and crafting potentially hundreds of items seems to make it a very arduous task.

Re: Minecraft diamond challenge leaves AI creators stumped

#23

Post by YeGoblynQueenne »

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 through self-play and without anything like an opening book of moves etc, like the origional AlphaGo architecture (or DeepBlue and traditional chess engines).

That is very big in AI right now, to try and remove the need for the "human in the loop" and learn complex tasks from 0 background knowledge.

Obviously, like you point out, this is very difficult to do and it requires lots and lots of data and compute (no, more than that. Really lots). As the article reports, this eliminates any hopes of "democratising" machine learning and makes advancing the state of the art a game that only large corporations can play with any hope of winning.

Re: Minecraft diamond challenge leaves AI creators stumped

#24

Post by coddle-hark »

mkagenius wrote: post #7
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.…

> single graphics processing unit (GPU) and four days of training time. Maybe there is a reason they had this restriction? I can only think of allowing the winning AI to be ready for end users whic h generally have a single GPU?

A level playing field is good for a challenge like this. Those that could solve it without these constraints are pushed to improve their existing approach. Those that don’t normally compete in these kind of challenges aren’t put off by a potential competitor having way more resources.

Re: Minecraft diamond challenge leaves AI creators stumped

#25

Post by milesvp »

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 resources is pretty easy to just dig down for.

The only thing that would make this hard is the thing that makes it hard for a human player which is knowing you’re on the diamond level without using the xyz debugging info.

Re: Minecraft diamond challenge leaves AI creators stumped

#26

Post by raverbashing »

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…

But there is a lot of "common knowledge" that's useful

All the problems solved by fine-tuning image net for example, instead of training from zero

Identifying objects in a 3D environment is useful across several domains and it shouldn't be limited to Minecraft

Re: Minecraft diamond challenge leaves AI creators stumped

#27

Post by imtringued »

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.

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 typing speed because the code is always the same but an AI with no prior knowledge can only brute force the solution. How does the speed runner win in the first place? They ask the game developer and then post the code on a wiki.

[0] an euphemism for minecrafts crafting system

Re: Minecraft diamond challenge leaves AI creators stumped

#28

Post by Jasper_ »

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…

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

Re: Minecraft diamond challenge leaves AI creators stumped

#29

Post by imtringued »

CrazyStat wrote: post #20
SquareWheel wrote: post #17

Earlier quoted context omitted.

It may be cheating, and sort of against the point, but those recipes are stored as json files. Makes things a lot easier.

It would be cheating. The contest rules [1] specifically rule out using domain knowledge. [1] https://gitlab.aicrowd.com/minerl/minerl-resources/blob/mast...

The humans finding diamonds in 20 minutes are cheaters by that logic.

Re: Minecraft diamond challenge leaves AI creators stumped

#30

Post by CrazyStat »

imtringued wrote: post #29
CrazyStat wrote: post #20

Earlier quoted context omitted.

It would be cheating. The contest rules [1] specifically rule out using domain knowledge. [1] https://gitlab.aicrowd.com/minerl/minerl-resources/blob/mast...

The humans finding diamonds in 20 minutes are cheaters by that logic.

Yes, a human competing in the AI challenge would be cheating.
Post reply on HN