News for hackers. Stuff that matters.
Re:AI masters Minecraft: DeepMind program finds diamonds wit... by IshKebab on Wednesday April 09, 2025 @03:51PM (#43636965)
Safely -> no crashes

Destination -> Like, close to the destination? I don't see how that's hard.

Happy -> you can use customer feedback for this

Folded -> this is indeed the trickiest one, but I think well within the capabilities of modern vision models.

Re:AI masters Minecraft: DeepMind program finds diamonds wit... by YeGoblynQueenne on Thursday April 10, 2025 @04:31AM (#43641931)
>> Safely -> no crashes

Really? What about fires? Falling off cliffs? Causing others to crash?

Your "examples" are all hand-wavy and vague and no good to train an RL agent. You've also not provided a reward function.