HackerTrans
TopNewTrendsCommentsPastAskShowJobs

hexhowells

no profile record

Submissions

The ML Trench

deep-ml-trench.vercel.app
1 points·by hexhowells·7 個月前·0 comments

Nth Country Experiment

en.wikipedia.org
3 points·by hexhowells·7 個月前·0 comments

In memory of the Christmas Island shrew

news.mongabay.com
79 points·by hexhowells·9 個月前·25 comments

The AI breakthrough that uses almost no power to create images

techxplore.com
3 points·by hexhowells·10 個月前·0 comments

Environments Hub: A Community Hub to Scale RL to Open AGI

primeintellect.ai
3 points·by hexhowells·11 個月前·0 comments

The Weight of a Cell

press.asimov.com
3 points·by hexhowells·11 個月前·0 comments

Understanding Moravec's Paradox

hexhowells.com
23 points·by hexhowells·11 個月前·12 comments

comments

hexhowells
·11 個月前·discuss
The human ability to learn from few examples can be explained with evolution (and thus search). We evolved to be fast learners as it was key to our survival. If you touched fire and felt pain, you better learn quickly not to keep touching it. This learning from reward signals (neurotransmitters) in our brain generalises to pretty much all learning tasks
hexhowells
·11 個月前·discuss
> Like a lot of human actions in space, folding clothes and other motor tasks are hierarchical sequences of smaller tasks that are strung together

I disagree, you can model those tasks as hiearchical sequences of smaller tasks. But the terminal goal of folding clothes is to turn a pile of unfolded clothes into a neat pile of folded clothes.

The reason you would break down the task is because getting between those two states with the only reward signal being "the clothes are now folded" takes a lot of steps, and given the possible actions the robot can take, results in a large search space.