31–40 of 113 posts
Sounds like a simple state machine. Don't they program objectives into their agents? Or are they relying purely on training?
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…
Title is misleading. Traditional AI with subroutines for each subtask would have no problem with this.
Title is misleading. Traditional AI with subroutines for each subtask would have no problem with this.
> Finding a diamond in Minecraft takes many steps - from cutting trees, to making tools, to exploring caves and actually finding a diamond. Sounds like a simple state machine. Don't they program objectives into their agents? Or are they relying purely on training?
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 can perhaps design a game that is difficult to solve by AI (though I wouldn't bet on it). The question with AI is usually not what it can't do but what it _can_ do. If a certain system fails at your task but performs well in a range of other tasks that are considered useful and challenging, then it's worth consideration. Especially so if there is no system that can perform well on that one task.
Title is misleading. Traditional AI with subroutines for each subtask would have no problem with this.
The challenge was to accomplish this without domain knowledge... if you can do this with GOFAI, please go ahead and shock the world.
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.
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…
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 highly addictive game).
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. 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?
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 like a human player. Also your network would likely be just blindly executing a series of learned actions, without any real understanding of the game. If you confronted it from some situation that's not part of some speedrun it memorized, it would probably be at a loss. Pretty useless.