News for hackers. Stuff that matters.

A comment on AI masters Minecraft: DeepMind program finds diamonds without being taught. Parent comment

Re:AI masters Minecraft: DeepMind program finds diamonds wit... by YeGoblynQueenne on Tuesday April 08, 2025 @06:31PM (#43627117)
>> Fold clothes -> clothes are folded.

>> Take children to school -> they safely arrive on time.

>> Autonomous driving -> arrive at destination without crashing.

>> Call centre -> customers are happy.

Define a) "folded", b) "safely", c) "destination", d) "happy".

Also define the reward functions for each of the four objectives above.

[ Parent | on HN ]
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.

[ Parent | on HN ]
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.

[ Parent | on HN ]