Re:Why traditional reinforcement learning will probably not ...
by joe_the_user on Wednesday October 21, 2020 @05:51PM
(#24852638)
Why couldn't a mechanism (say A Neural Turing or whatever) that you train be "cognition capable" when you start and then be trained to actual behavior after that?
[ Parent
| on HN ]
Re:Why traditional reinforcement learning will probably not ...
by benchaney on Wednesday October 21, 2020 @07:54PM
(#24853614)
You would need something that is "cognition capable" first and that has not been invented yet.
Re:Why traditional reinforcement learning will probably not ...
by joe_the_user on Thursday October 22, 2020 @12:47AM
(#24854981)
It's hard to know. Maybe something "cognition cable" exists, it's just the proper train routine hasn't been provided to it.
But regardless, the broader point is yeah, combine something akin cognition capability and the proper training routine and there you go, AGI from "reinforcement learning", broadly defined.