it’s hard to see any obvious way in which the rubik’s demo is more impressive than the more flexible Google Brain Baoding demo that came out earlier in the month. what do you think @beenwrekt?
-
They definitely didn't solve that problem, but did make progress on a much simpler problem that hadn't been previously solved. I'm confident its an advance because the bar is *so* low. Getting a shadow hand to do anything is difficult, as is closing the simulation gap.
so what is the specific problem you do think they solved and what do think it’s scope and limits are?
-
-
I wouldn't say they "solved" anything. They made progress on the problem of getting the shadow hand to perform a dextrous manipulation task via sim2real. Shouldn't have to speculate about the future capabilities to appreciate that.
-
wow! imagine if the title of the paper had been the modest and accurate “progress on the problem getting a shadow hand to perform a dextrous manipulation hand via sim2real”.
@OpenAI you wouldn’t have heard a peep from me.
End of conversation
New conversation -
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.