Live data from Hacker News

Minecraft diamond challenge leaves AI creators stumped

bbc.co.uk

11–20 of 113 posts

Re: Minecraft diamond challenge leaves AI creators stumped

#13

> 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?

The resources devoted to training don't really translate to the resources needed to run the trained model. A model trained on a thousand GPUS for a week might still run in real time on a single GPU once trained.

The restricted training resources are just part of the challenge. They point out that a human child can learn the necessary steps in minutes by watching someone else do it, so they wanted to see if anyone could make a computer learn it with relatively limited resources.

Re: Minecraft diamond challenge leaves AI creators stumped

#14
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…

They had 60 million frames of video (about 277 hours, assuming 60fps) to show to the computer for it to learn how. I think a human player could pick it up in that time.

Re: Minecraft diamond challenge leaves AI creators stumped

#15

I take it no one's submitted Baritone [0] yet? Or would that be against the spirit of the contest? [0] https://github.com/cabaletta/baritone

That would be against the letter of the challenge, not to mention the spirit. From the rules [1]:

> The submission must train a machine learning model without relying heavily on human domain knowledge. A manually specified policy may not be used as a component of this model. Likewise, the reward function may not be changed (shaped) based on manually engineered, hard-coded functions of the state. For example, though a learned hierarchical controller is permitted, meta-controllers may not choose between two policies based on a manually specified function of the state, such as whether the agent has a certain item in its inventory. Similarly, additional rewards for approaching tree-like objects are not permitted, but rewards for encountering novel states (“curiosity rewards”) are permitted.

[1] https://gitlab.aicrowd.com/minerl/minerl-resources/blob/mast...

Re: Minecraft diamond challenge leaves AI creators stumped

#16

> 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?

Imposing constraints forces people to be more creative in their approach. This seems like it was explicitly a goal of the challenge, to find more clever ways to solve problems without just relying on more data.

They're just biasing competitors towards efficient solutions.

Re: Minecraft diamond challenge leaves AI creators stumped

#17

Earlier quoted context omitted.

Minecraft has had a native recipe book for some time. It displays crafting recipes as you progress through the game.

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.

Re: Minecraft diamond challenge leaves AI creators stumped

#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 focus on task discovery.

If anyone had pass the bar this challenge set, they'd have basically solved the biggest hurdle in general AI, and would probably have received a call from John Carmack.

Re: Minecraft diamond challenge leaves AI creators stumped

#19

My google-fu is failing. I see this and copies of this article, but I want to know more about the I/O available to the AI. Did the AI get full access to the Minecraft API or were they limited audio, video, keyboard, mouse like a human player?

The documentation [1] has details. For input they get an RGB image (i.e. what a player would see on the screen, minus the UI) and other relevant information (e.g. inventory). For output they have to specify from a list of possible actions that they can take: move forward, move back, craft an item, etc.

[1] http://minerl.io/docs/tutorials/index.html

Re: Minecraft diamond challenge leaves AI creators stumped

#20

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.

It would be cheating. The contest rules [1] specifically rule out using domain knowledge.

[1] https://gitlab.aicrowd.com/minerl/minerl-resources/blob/mast...

Post reply on HN